© 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. 19-RESID-POST-AA
    6. 111687
    Prev
    Next
    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pool
    -0.06
    avian
    -0.06
     Phạm
    -0.06
    _msg
    -0.06
     gql
    -0.06
     "",
    -0.06
     фіз
    -0.06
    h
    -0.06
    明白
    -0.06
    got
    -0.06
    POSITIVE LOGITS
    >(*
    0.07
    CADE
    0.06
     employers
    0.06
    (expected
    0.06
    gist
    0.06
    npc
    0.06
     efficacy
    0.06
     सम
    0.06
     Admission
    0.06
     thematic
    0.06
    Activations Density 0.036%

    No Known Activations