Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 23-RESID-POST-AA
    6. 103943
    Prev
    Next
    INDEX
    Explanations

    pv

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     exterior
    -0.07
     cela
    -0.06
    iap
    -0.06
    füg
    -0.06
    secret
    -0.06
    ieten
    -0.06
     releases
    -0.06
    рии
    -0.06
    cache
    -0.06
     junge
    -0.06
    POSITIVE LOGITS
     OnCollision
    0.08
     εμπ
    0.07
     팀
    0.07
     comunic
    0.07
     киш
    0.07
     поруш
    0.06
    №№№№
    0.06
    ]=>
    0.06
     renderItem
    0.06
    _KeyPress
    0.06
    Activations Density 0.003%

    No Known Activations