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. 120419
    Prev
    Next
    INDEX
    Explanations

    isoenzymes, isoforms

    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
     cold
    -0.07
     Cold
    -0.07
    ibrated
    -0.06
    /IP
    -0.06
    	B
    -0.06
    软
    -0.06
    Vault
    -0.06
    slack
    -0.06
     store
    -0.06
     dal
    -0.06
    POSITIVE LOGITS
    _emlrt
    0.07
    .jsdelivr
    0.07
     chefs
    0.06
     _↵
    0.06
    (datas
    0.06
    _pdata
    0.06
    )object
    0.06
    (parcel
    0.06
    createQuery
    0.06
     مؤ
    0.06
    Activations Density 0.041%

    No Known Activations