Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 9776
    Prev
    Next
    INDEX
    Explanations

    keep

    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
    mouseup
    -0.07
    道路
    -0.07
    GINE
    -0.07
    特殊
    -0.06
    _RSP
    -0.06
    span
    -0.06
     Lug
    -0.06
     yoga
    -0.06
    기로
    -0.06
    789
    -0.06
    POSITIVE LOGITS
     keep
    0.15
     keeps
    0.12
     kept
    0.11
     Keep
    0.10
    Keep
    0.10
     keeping
    0.09
     Keeping
    0.09
     KEEP
    0.08
    keep
    0.08
     преп
    0.07
    Activations Density 0.026%

    No Known Activations