© 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. 109494
    Prev
    Next
    INDEX
    Explanations

    varied text sources

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of being “outside of” a group or collective context.

    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
    του
    -0.06
    _DELAY
    -0.06
    �
    -0.06
    Chuck
    -0.06
     Rigidbody
    -0.05
    _lambda
    -0.05
    �n
    -0.05
    선
    -0.05
    .keep
    -0.05
     Ngọc
    -0.05
    POSITIVE LOGITS
    MENT
    0.08
     postpon
    0.07
     lesbi
    0.07
    $post
    0.07
     професій
    0.07
     elev
    0.06
    :end
    0.06
     conscient
    0.06
    aseline
    0.06
     bel
    0.06
    Activations Density 0.000%

    No Known Activations