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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 54418
    Prev
    Next
    INDEX
    Explanations

    possessive

    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
    chair
    -0.08
    _glyph
    -0.06
     �
    -0.06
    ظ
    -0.06
     Nob
    -0.06
     boil
    -0.06
     contingency
    -0.06
     cooperative
    -0.06
     eventData
    -0.06
     Giant
    -0.06
    POSITIVE LOGITS
    _set
    0.06
     conhec
    0.06
     ontvang
    0.06
    егор
    0.06
     pagan
    0.06
    ramework
    0.06
     strncmp
    0.06
    AGR
    0.06
     resolving
    0.06
     Handy
    0.06
    Activations Density 0.009%

    No Known Activations