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. 126819
    Prev
    Next
    INDEX
    Explanations

    code errors

    np_max-act · gemini-2.0-flash

    The neuron detects instances of shell error messages indicating that a command was not found.

    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
    wcsstore
    -0.08
     yc
    -0.07
    Ru
    -0.06
    omes
    -0.06
    Nm
    -0.06
     경기도
    -0.06
    ढ
    -0.06
     pik
    -0.06
    SFML
    -0.06
    orm
    -0.06
    POSITIVE LOGITS
     figured
    0.07
    ivre
    0.07
    objc
    0.07
    PIPE
    0.07
     libre
    0.07
    攻击
    0.07
    ?",↵
    0.06
     Inline
    0.06
    "`↵
    0.06
    EqualityComparer
    0.06
    Activations Density 0.030%

    No Known Activations