© 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. 126781
    Prev
    Next
    INDEX
    Explanations

    close

    np_max-act · gemini-2.0-flash

    The neuron fires on the markers that begin or end fenced code sections (e.g. the triple-backtick lines).

    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
    _ADD
    -0.06
    .Art
    -0.06
    chet
    -0.06
    _EST
    -0.06
    bill
    -0.06
     ann
    -0.06
    uyen
    -0.06
    _var
    -0.06
    .soft
    -0.06
    /App
    -0.06
    POSITIVE LOGITS
     complexes
    0.08
     complex
    0.07
    면서
    0.07
    Along
    0.07
     convention
    0.07
     accred
    0.07
     života
    0.07
     todas
    0.07
    IVER
    0.07
     chromosome
    0.07
    Activations Density 0.006%

    No Known Activations