© 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. 91476
    Prev
    Next
    INDEX
    Explanations

    @

    np_max-act · gemini-2.0-flash

    technical terminology and concepts related to ion channels and their role in cellular processes.

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

    The neuron detects in-text reference citations or bibliography markers (e.g. bracketed/superscripted citation notations).

    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
     Shapiro
    -0.07
    eties
    -0.07
    _mode
    -0.07
    salary
    -0.07
     similarly
    -0.07
     ice
    -0.07
    rs
    -0.07
     form
    -0.07
     silenced
    -0.07
    ayas
    -0.06
    POSITIVE LOGITS
    (EIF
    0.06
    ニニニニ
    0.06
     والتي
    0.06
    .MULT
    0.06
    .GeneratedValue
    0.06
    setDefault
    0.06
    ovíd
    0.06
    Interceptor
    0.05
     دش
    0.05
     çiz
    0.05
    Activations Density 0.042%

    No Known Activations