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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 41875
    Prev
    Next
    INDEX
    Explanations

    up

    np_max-act · gemini-2.0-flash

    detective work and investigation themes in narratives.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron detects past‐tense motion/action verbs (e.g. “stood,” “walked”) indicating a character physically moving.

    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
     packaged
    -0.07
    _datasets
    -0.06
    (END
    -0.06
     xmlDoc
    -0.06
    (getClass
    -0.06
    Mismatch
    -0.06
    ¨ط
    -0.06
     screened
    -0.06
    PLIER
    -0.06
    _userid
    -0.06
    POSITIVE LOGITS
     количество
    0.07
     उठ
    0.07
    unate
    0.07
    ocial
    0.06
    ursively
    0.06
    eon
    0.06
     spur
    0.06
    дн
    0.06
    升
    0.06
    стор
    0.06
    Activations Density 0.010%

    No Known Activations