© 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. 54352
    Prev
    Next
    INDEX
    Explanations

    book titles/excerpts

    np_max-act · gemini-2.0-flash

    The neuron flags words that are parts of book or series titles (e.g. proper-noun title fragments).

    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
     annunci
    -0.06
    _air
    -0.06
    ÄŸ
    -0.06
    .key
    -0.06
    과의
    -0.06
     operations
    -0.06
    ِّ
    -0.06
     Cargo
    -0.06
     MF
    -0.06
    -th
    -0.06
    POSITIVE LOGITS
    Cop
    0.07
    یکی
    0.07
     RuntimeObject
    0.07
    owej
    0.07
     Ebony
    0.07
    λευ
    0.06
     Особ
    0.06
     Ви
    0.06
     Montgomery
    0.06
     lục
    0.06
    Activations Density 0.120%

    No Known Activations