© 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. 30128
    Prev
    Next
    INDEX
    Explanations

    Departing

    np_max-act · gemini-2.0-flash

    The neuron activates on placeholder tokens that include an underscore followed by a digit (e.g. “NAME_1”), i.e. character‐identifier tokens.

    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
    .JSONException
    -0.07
     Mos
    -0.07
    .IN
    -0.07
     nuest
    -0.07
     ringing
    -0.06
    (ip
    -0.06
     productName
    -0.06
     lubric
    -0.06
     pharmacist
    -0.06
     accommodation
    -0.06
    POSITIVE LOGITS
    }).
    0.07
    ский
    0.07
    ,''
    0.07
    楚
    0.07
    -setup
    0.06
     Special
    0.06
    怕
    0.06
     mafia
    0.06
    еним
    0.06
     seasonal
    0.06
    Activations Density 0.036%

    No Known Activations