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

    Neuronpedia

    APICircuit 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. 11-RESID-POST-AA
    6. 104348
    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ��
    -0.06
    epar
    -0.06
    Зап
    -0.06
     xảy
    -0.06
     panor
    -0.06
    	align
    -0.06
     вій
    -0.06
    대비
    -0.06
     tímto
    -0.06
    Mar
    -0.05
    POSITIVE LOGITS
     Afghan
    0.07
     buds
    0.07
    .faces
    0.07
     integers
    0.07
     conject
    0.07
    ган
    0.07
    =NULL
    0.07
    >S
    0.07
     arkadaş
    0.06
    ñ
    0.06
    Activations Density 0.014%

    No Known Activations