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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 11-RESID-POST-AA
    6. 74752
    Prev
    Next
    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash

    The neuron flags list‐introducing phrases—especially “Here are …” or similar cues that precede a set of recommendations or enumerated items.

    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
     KBS
    -0.07
     Celtics
    -0.06
     cwd
    -0.06
    Dup
    -0.06
    GPIO
    -0.06
     relentless
    -0.06
    iction
    -0.05
     probí
    -0.05
     SUP
    -0.05
     chron
    -0.05
    POSITIVE LOGITS
    альные
    0.07
    _orient
    0.07
     شكل
    0.07
    松
    0.07
     가져
    0.07
    Authenticate
    0.07
     convey
    0.07
    нять
    0.07
    ανά
    0.06
    Suggestions
    0.06
    Activations Density 0.018%

    No Known Activations