© 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
    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. 27387
    Prev
    Next
    INDEX
    Explanations

    Music albums, songs

    np_max-act · gemini-2.0-flash

    song titles and album names.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    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
    )index
    -0.07
    ानव
    -0.07
    霞
    -0.07
    dictions
    -0.06
    jah
    -0.06
     ":"
    -0.06
    ुक
    -0.06
    Ь
    -0.06
    ینک
    -0.06
    elda
    -0.06
    POSITIVE LOGITS
    (serializer
    0.07
    yard
    0.07
    stacle
    0.06
    .graphics
    0.06
     编
    0.06
    FromString
    0.06
    &e
    0.06
    64
    0.06
    Embedded
    0.06
     Tuy
    0.06
    Activations Density 0.010%

    No Known Activations