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. 26216
    Prev
    Next
    INDEX
    Explanations

    error

    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
     volum
    -0.07
    ,index
    -0.07
     AMP
    -0.06
     displayName
    -0.06
    _IB
    -0.06
     electr
    -0.06
    istributor
    -0.06
    ubat
    -0.06
     Suche
    -0.06
    agination
    -0.06
    POSITIVE LOGITS
    ModelError
    0.07
    	il
    0.07
    ไซ
    0.06
     Stall
    0.06
     ورزشی
    0.06
    Statements
    0.06
     следующие
    0.06
    ()
    ↵
    ↵
    ↵
    0.06
     εμφ
    0.06
     -*-↵↵
    0.06
    Activations Density 0.002%

    No Known Activations