© 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. 6226
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    The neuron strongly responds to noun phrases that are being “given,” “eaten,” “watched,” etc. – in other words, it tends to pick out the direct‐object nouns in a sentence.

    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
    avaş
    -0.06
    tell
    -0.06
    ยะ
    -0.06
     cooked
    -0.06
    Pu
    -0.06
     GOLD
    -0.06
    IGNAL
    -0.06
    Through
    -0.06
    -ln
    -0.06
    Tell
    -0.06
    POSITIVE LOGITS
     Evo
    0.07
     *.
    0.06
     screenSize
    0.06
     //////////////////////////////////////////////////////////////////////////
    0.06
    uitka
    0.06
     Veterinary
    0.06
    **)
    0.06
     yanıt
    0.06
    .readFileSync
    0.06
     pund
    0.06
    Activations Density 0.089%

    No Known Activations