© 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. 7-RESID-POST-AA
    11. 108645
    Prev
    Next
    INDEX
    Explanations

    Redacted information

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     extradition
    -0.06
     Brief
    -0.06
     Blanc
    -0.06
    _out
    -0.06
    lic
    -0.06
    memo
    -0.06
     postupně
    -0.06
    eper
    -0.06
     سرو
    -0.06
    ‏
    -0.06
    POSITIVE LOGITS
    ']."</
    0.07
    .rpm
    0.06
    "os
    0.06
    .exist
    0.06
    =models
    0.06
     dab
    0.06
    ockey
    0.06
    Pieces
    0.06
    elay
    0.06
     Tape
    0.06
    Activations Density 0.001%

    No Known Activations