© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 46842
    Prev
    Next
    INDEX
    Explanations

    Long text excerpts

    np_max-act · gemini-2.0-flash

    rationale based on events and character decisions in narratives.

    oai_token-act-pair · gpt-4o-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
     schizophrenia
    -0.07
    دار
    -0.07
    ADC
    -0.06
    andoned
    -0.06
    .eval
    -0.06
    ivalent
    -0.06
    Confirmation
    -0.06
    auge
    -0.06
    を行
    -0.06
     Siemens
    -0.06
    POSITIVE LOGITS
    Billing
    0.06
    _WARN
    0.06
     минут
    0.06
    .arch
    0.06
     hurdle
    0.06
    —↵↵
    0.06
     Tư
    0.06
     Nr
    0.06
     '"
    0.06
    (ChatColor
    0.06
    Activations Density 0.027%

    No Known Activations