© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 6414
    Prev
    Next
    INDEX
    Explanations

    file paths

    np_max-act · gemini-2.0-flash

    The neuron is sensitive to any token containing numeric digits, such as version numbers or path components with numbers.

    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
    есь
    -0.06
    Unmount
    -0.06
     Mik
    -0.06
     teammate
    -0.06
    ПО
    -0.06
     které
    -0.06
    /card
    -0.05
    CLUSIVE
    -0.05
    bor
    -0.05
    loop
    -0.05
    POSITIVE LOGITS
     cpf
    0.07
     indign
    0.07
    .addAction
    0.07
     포
    0.07
     pstmt
    0.07
    (getString
    0.07
     ー
    0.06
     zahrn
    0.06
     Differential
    0.06
     Basel
    0.06
    Activations Density 0.006%

    No Known Activations