© 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. 109176
    Prev
    Next
    INDEX
    Explanations

    Format

    np_max-act · gemini-2.0-flash

    The neuron fires specifically on the literal “Format” token (as in a file‐header metadata field).

    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
    Jamie
    -0.06
     Ronnie
    -0.06
     Updates
    -0.06
     Nav
    -0.06
     mnoha
    -0.06
    .apache
    -0.06
    mış
    -0.06
    -basket
    -0.05
     Destructor
    -0.05
    ]
    -0.05
    POSITIVE LOGITS
    _prior
    0.07
    кти
    0.07
     Realt
    0.07
    져
    0.07
    getStatusCode
    0.07
     ولی
    0.07
    /footer
    0.06
     ولم
    0.06
    .scene
    0.06
    یا
    0.06
    Activations Density 0.001%

    No Known Activations