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. 121624
    Prev
    Next
    INDEX
    Explanations

    after

    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
     ово
    -0.07
    seven
    -0.06
     RECORD
    -0.06
     :\
    -0.06
    üç
    -0.06
    ��
    -0.06
     nobody
    -0.06
     gà
    -0.05
     伊
    -0.05
    PLETED
    -0.05
    POSITIVE LOGITS
    brace
    0.07
     ValidationError
    0.07
     RequestContext
    0.07
    _RESOURCE
    0.07
    _dep
    0.07
    .ToString
    0.07
    .encrypt
    0.06
     dara
    0.06
    tokenizer
    0.06
     walkers
    0.06
    Activations Density 0.000%

    No Known Activations