Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 84607
    Prev
    Next
    INDEX
    Explanations

    semicolon

    np_max-act · gemini-2.0-flash

    This neuron fires on identifiers in import statements, picking up package/class names in import declarations.

    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
     previews
    -0.07
    ραβ
    -0.06
    iggs
    -0.06
     statistics
    -0.06
     Famil
    -0.06
     Grants
    -0.06
     Hz
    -0.06
    -party
    -0.06
    umbles
    -0.06
    tod
    -0.06
    POSITIVE LOGITS
    eturn
    0.07
     webcam
    0.06
     madness
    0.06
     ".$
    0.06
    ]})↵
    0.06
     entertained
    0.06
     mesmer
    0.06
    ��
    0.06
    ?>↵
    0.06
    การศ
    0.06
    Activations Density 0.023%

    No Known Activations