© 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. 562
    Prev
    Next
    INDEX
    Explanations

    eta

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on technical characterization and measurement terms in scientific reports—e.g. zeta potential, particle size, electron microscopy, dynamic light scattering, and related analysis jargon.

    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
    ELEMENT
    -0.07
    дивиду
    -0.06
    )}>↵
    -0.06
    ///↵
    -0.06
     Mour
    -0.06
    _kel
    -0.06
    iona
    -0.06
    ())));↵
    -0.06
    _STA
    -0.06
    _MON
    -0.06
    POSITIVE LOGITS
     próximo
    0.07
     setHidden
    0.07
    �
    0.07
    ड़क
    0.07
     dış
    0.06
     cùng
    0.06
     alg
    0.06
    .jackson
    0.06
     тщ
    0.06
     mé
    0.06
    Activations Density 0.004%

    No Known Activations