© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 71759
    Prev
    Next
    INDEX
    Explanations

    }

    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
     insurer
    -0.07
     международ
    -0.07
    ，她
    -0.06
    ventory
    -0.06
     btc
    -0.06
     Playing
    -0.06
    523
    -0.06
     stringValue
    -0.06
     sad
    -0.06
     sofa
    -0.06
    POSITIVE LOGITS
    .White
    0.06
    okino
    0.06
    kening
    0.06
    uell
    0.06
    ーリ
    0.06
    采用
    0.06
    ~↵
    0.05
     vòng
    0.05
    ヾ
    0.05
    ekl
    0.05
    Activations Density 0.012%

    No Known Activations