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. 125495
    Prev
    Next
    INDEX
    Explanations

    Best

    np_max-act · gemini-2.0-flash

    The neuron fires on phrasing that describes generating multiple candidate solutions and selecting or ranking the top one.

    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
     '+
    -0.06
     Richmond
    -0.06
     domest
    -0.06
     NODE
    -0.06
    .grp
    -0.06
     anguish
    -0.06
    .sup
    -0.06
    coords
    -0.06
    ein
    -0.05
    "sync
    -0.05
    POSITIVE LOGITS
     xét
    0.07
     Enlightenment
    0.07
     cravings
    0.06
    adir
    0.06
    IRS
    0.06
    佛
    0.06
     асп
    0.06
    ieme
    0.06
    /K
    0.06
    先
    0.06
    Activations Density 0.027%

    No Known Activations