© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 92163
    Prev
    Next
    INDEX
    Explanations

    string formatting

    np_max-act · gemini-2.0-flash

    The neuron fires on the Python f‐string format specifier (the leading “f” before string literals).

    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
    ็นต
    -0.07
     Ud
    -0.07
    (user
    -0.07
    _zero
    -0.06
    eria
    -0.06
     uzav
    -0.06
    (td
    -0.06
     пля
    -0.06
     oby
    -0.06
     елем
    -0.06
    POSITIVE LOGITS
    fixtures
    0.07
    Picture
    0.07
     causes
    0.07
    VF
    0.06
    (filters
    0.06
    propri
    0.06
    .printf
    0.06
    _messages
    0.06
    019
    0.06
    Frequency
    0.06
    Activations Density 0.003%

    No Known Activations