Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 73440
    Prev
    Next
    INDEX
    Explanations

    holder

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of “holder” (and its variants) referring to a component that holds or supports another part.

    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
    /p
    -0.07
     beverages
    -0.06
     Expl
    -0.06
     predicting
    -0.06
     sulph
    -0.06
    /G
    -0.06
     stimulate
    -0.06
     推
    -0.06
    /w
    -0.06
     drops
    -0.06
    POSITIVE LOGITS
     acompanh
    0.07
     disrespectful
    0.07
    대
    0.06
    .consumer
    0.06
     outer
    0.06
    병
    0.06
     harbor
    0.06
     자신의
    0.06
    ')),↵
    0.06
    реп
    0.06
    Activations Density 0.039%

    No Known Activations