© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 110233
    Prev
    Next
    INDEX
    Explanations

    pronouns

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on occurrences of the verb “give” (in forms like “give” and “giving”).

    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
    인이
    -0.09
     Can
    -0.08
    .onPause
    -0.07
    when
    -0.07
    could
    -0.07
     Fun
    -0.07
    HELP
    -0.07
    .Can
    -0.07
    -can
    -0.07
     when
    -0.06
    POSITIVE LOGITS
     given
    0.10
    >
    0.07
     gave
    0.07
     général
    0.07
     اتاق
    0.06
    余
    0.06
     financ
    0.06
    CEEDED
    0.06
     개
    0.06
     Offer
    0.06
    Activations Density 0.047%

    No Known Activations