© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 6585
    Prev
    Next
    INDEX
    Explanations

    proper nouns

    np_max-act · gemini-2.0-flash

    This neuron detects the placeholder “NAME_” tokens (i.e. the NAME_x variables) in the text.

    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
    .FlatStyle
    -0.07
    InternalEnumerator
    -0.07
     бу
    -0.06
     Instagram
    -0.06
    (models
    -0.06
     Middle
    -0.06
    _Method
    -0.06
    Saint
    -0.06
    sup
    -0.06
    Porno
    -0.06
    POSITIVE LOGITS
    -project
    0.07
    부터
    0.07
     ASSIGN
    0.07
     SHE
    0.07
    Instrument
    0.06
    omanip
    0.06
    /response
    0.06
     aktif
    0.06
     hareket
    0.06
    /sm
    0.06
    Activations Density 0.089%

    No Known Activations