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. 23-RESID-POST-AA
    6. 40699
    Prev
    Next
    INDEX
    Explanations

    Definition of terms

    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
    iag
    -0.07
    _↵
    -0.07
     minutos
    -0.07
    %↵
    -0.06
    whereIn
    -0.06
     		↵
    -0.06
    保護
    -0.06
     diag
    -0.06
     Maison
    -0.06
    SETTING
    -0.06
    POSITIVE LOGITS
    ¨
    0.07
    耗
    0.07
    Adam
    0.06
    000
    0.06
     LSM
    0.06
    .consume
    0.06
     statt
    0.06
     commun
    0.06
    .mime
    0.06
     Kiss
    0.06
    Activations Density 0.000%

    No Known Activations