© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 85727
    Prev
    Next
    INDEX
    Explanations

    challenges

    np_max-act · gemini-2.0-flash

    The neuron is detecting words that signal challenges, difficulties, or barriers (e.g., “major,” “difficulties,” “barriers,” “limitations”).

    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
     validationResult
    -0.08
    _journal
    -0.07
     فهرست
    -0.06
     role
    -0.06
     bible
    -0.06
     medium
    -0.06
     روند
    -0.06
    ContentAlignment
    -0.06
    ापक
    -0.06
     їх
    -0.06
    POSITIVE LOGITS
     ALERT
    0.06
    halten
    0.06
     steals
    0.06
     entren
    0.06
    phant
    0.06
    ritable
    0.06
    geist
    0.06
     barrels
    0.06
     [.
    0.06
    .HORIZONTAL
    0.06
    Activations Density 0.068%

    No Known Activations