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. 7-RESID-POST-AA
    6. 106736
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     polarization
    -0.07
     analytics
    -0.07
    slack
    -0.06
    الی
    -0.06
    icios
    -0.06
    -by
    -0.06
    =str
    -0.06
     waves
    -0.06
     designer
    -0.06
     shop
    -0.06
    POSITIVE LOGITS
    @synthesize
    0.07
     EVENTS
    0.07
     withdrawals
    0.07
    ???↵↵
    0.07
     blah
    0.07
    ,而且
    0.06
     appropri
    0.06
     милли
    0.06
    ?」↵↵
    0.06
     seksi
    0.06
    Activations Density 0.080%

    No Known Activations