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. 15-RESID-POST-AA
    6. 74625
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    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
    .children
    -0.07
    ो।
    -0.07
    .SetParent
    -0.06
    写
    -0.06
    ।
    -0.06
     markings
    -0.06
    Psy
    -0.06
     tudo
    -0.06
     timespec
    -0.06
         
    -0.06
    POSITIVE LOGITS
     garner
    0.07
    (--
    0.07
     collar
    0.06
    .Texture
    0.06
     blend
    0.06
    erspective
    0.06
     زمان
    0.06
    (using
    0.06
    (ALOAD
    0.06
    _TYPE
    0.06
    Activations Density 0.028%

    No Known Activations