© 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
    4. Resid Post - 131k
    5. 15-RESID-POST-AA
    6. 128482
    Prev
    Next
    INDEX
    Explanations

    legal proceedings

    np_max-act · gemini-2.0-flash

    Detects mentions of pretrial release or detention and the conditions/decisions around whether a defendant is held or released.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Warnings
    -0.07
     Canonical
    -0.07
    �
    -0.06
     brewers
    -0.06
     MAIN
    -0.06
    -power
    -0.06
    _record
    -0.06
    heed
    -0.06
    etas
    -0.06
     scripts
    -0.06
    POSITIVE LOGITS
    [data
    0.07
     Şehir
    0.06
    Meg
    0.06
     готов
    0.06
    	Scanner
    0.06
    @return
    0.06
    _wo
    0.06
     vide
    0.06
    VIRTUAL
    0.06
    $res
    0.06
    Activations Density 0.015%

    No Known Activations