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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 7-RESID-POST-AA
    6. 58065
    Prev
    Next
    INDEX
    Explanations

    timely

    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
    oure
    -0.07
    cko
    -0.07
    great
    -0.06
     '^
    -0.06
    /screens
    -0.06
    fait
    -0.06
     nuevo
    -0.06
    urgeon
    -0.06
    çon
    -0.06
     Aura
    -0.06
    POSITIVE LOGITS
     timely
    0.16
     promptly
    0.08
     equitable
    0.07
     Dipl
    0.07
     biomedical
    0.06
    Last
    0.06
     �
    0.06
    ely
    0.06
    .weixin
    0.06
    :self
    0.06
    Activations Density 0.004%

    No Known Activations