© 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
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 112194
    Prev
    Next
    INDEX
    Explanations

    Ship construction

    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
     Dallas
    -0.07
    -force
    -0.06
    hidden
    -0.06
     INS
    -0.06
     sequences
    -0.06
    communication
    -0.06
     snakes
    -0.06
    Spawn
    -0.05
     Reduction
    -0.05
    @qq
    -0.05
    POSITIVE LOGITS
     süreci
    0.06
    /memory
    0.06
     вне
    0.06
     bikini
    0.06
    pus
    0.06
    _pcm
    0.06
     usr
    0.06
    urved
    0.06
     Každ
    0.06
    ocusing
    0.06
    Activations Density 0.018%

    No Known Activations