© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 30184
    Prev
    Next
    INDEX
    Explanations

    Relationships between entities

    np_max-act · gemini-2.0-flash

    terms related to cellular structures and communications within the central nervous system.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron selectively responds to mentions of glial cell types and their intercellular junctions (e.g. astrocytes, oligodendrocytes, connexins, gap junction interactions).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WAIT
    -0.07
     Towers
    -0.06
    [url
    -0.06
    GD
    -0.06
     QPainter
    -0.06
    ™
    -0.06
    property
    -0.06
     fwd
    -0.06
    EQ
    -0.06
     chances
    -0.06
    POSITIVE LOGITS
    Failure
    0.07
     fatto
    0.06
    OptionsItemSelected
    0.06
     Recovery
    0.06
    idden
    0.06
     hemos
    0.06
    Rio
    0.06
    .div
    0.06
    리
    0.06
     Enrique
    0.06
    Activations Density 0.109%

    No Known Activations