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. 11-RESID-POST-AA
    6. 73331
    Prev
    Next
    INDEX
    Explanations

    intro

    np_max-act · gemini-2.0-flash

    album titles and track listings from musical releases.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron detects the formatting and structural elements of music album track listings, such as section labels and time‐stamp annotations.

    oai_token-act-pair · o4-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
     ContentValues
    -0.06
     CELL
    -0.06
     Tiles
    -0.06
    нич
    -0.06
    Kelly
    -0.06
    plex
    -0.06
     Christine
    -0.06
    ı
    -0.06
     name
    -0.06
     Kelly
    -0.06
    POSITIVE LOGITS
    mlink
    0.07
    .t
    0.06
    .|
    0.06
     embedded
    0.06
    tober
    0.06
     clay
    0.06
     dyn
    0.06
     peninsula
    0.06
     /↵
    0.06
     conc
    0.06
    Activations Density 0.017%

    No Known Activations