© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 92088
    Prev
    Next
    INDEX
    Explanations

    ed

    np_max-act · gemini-2.0-flash

    This neuron selectively activates on tokens typical of bibliographic references—e.g. edition/“eds” markers, years, page‐number numerals, and similar citation metadata.

    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
     Brush
    -0.07
    Demon
    -0.07
    От
    -0.07
    �
    -0.07
     foe
    -0.07
    "But
    -0.07
    .prot
    -0.07
    _FMT
    -0.07
     Madagascar
    -0.06
     �
    -0.06
    POSITIVE LOGITS
     eds
    0.07
     cooling
    0.06
     ed
    0.06
     вс
    0.06
    령
    0.06
    least
    0.06
    소년
    0.06
     mainly
    0.06
     Various
    0.06
     adolescence
    0.06
    Activations Density 0.002%

    No Known Activations