© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 56052
    Prev
    Next
    INDEX
    Explanations

    Alb

    np_max-act · gemini-2.0-flash

    references to football teams and their performance in the Liga MX.

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

    The neuron primarily responds to numeric tokens—digits, scores, dates, and other number‐related strings.

    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
    .Home
    -0.07
    prising
    -0.07
     vượt
    -0.07
    (service
    -0.07
     radians
    -0.07
     towers
    -0.07
     cùng
    -0.06
     deriving
    -0.06
     persist
    -0.06
     released
    -0.06
    POSITIVE LOGITS
     intrusion
    0.06
    (Throwable
    0.06
     Gang
    0.06
    善
    0.05
    getStatusCode
    0.05
    .aut
    0.05
     getItem
    0.05
    DES
    0.05
     hamm
    0.05
     Chili
    0.05
    Activations Density 0.065%

    No Known Activations