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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 15-RESID-POST-AA
    6. 80846
    Prev
    Next
    INDEX
    Explanations

    Numbered or lettered lists

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     uur
    -0.07
    �
    -0.06
    ips
    -0.06
     frags
    -0.06
     superficial
    -0.06
    bou
    -0.06
     younger
    -0.06
    apse
    -0.06
     Kong
    -0.06
     entra
    -0.06
    POSITIVE LOGITS
     Individuals
    0.06
    imately
    0.06
     Returns
    0.06
    calc
    0.06
    (SDL
    0.06
    (errors
    0.06
     millions
    0.06
    .apps
    0.06
     üzere
    0.06
    _unused
    0.06
    Activations Density 0.030%

    No Known Activations