© 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. 73997
    Prev
    Next
    INDEX
    Explanations

    Code/syntax related

    np_max-act · gemini-2.0-flash

    The neuron fires on words and phrases used in refusals or policy compliance around harmful content—especially terms like “racism,” “discrimination,” “toxic,” and “behavior.”

    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
     Nothing
    -0.07
     paid
    -0.07
     Imm
    -0.06
     Govern
    -0.06
     после
    -0.06
     NOTHING
    -0.06
    ildren
    -0.06
     type
    -0.06
     icy
    -0.06
    older
    -0.06
    POSITIVE LOGITS
     fromDate
    0.06
     ingresar
    0.06
     图
    0.06
     IllegalAccessException
    0.06
    dent
    0.06
     ';
    ↵
    0.06
    -C
    0.06
    .article
    0.06
    �
    0.06
    }));↵↵
    0.06
    Activations Density 0.025%

    No Known Activations