© 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. 7910
    Prev
    Next
    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash

    This neuron fires on tokens that represent named‐entity labels (e.g. PERSON, LOCATION, ORGANIZATION) in the NER output format.

    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
    ưở
    -0.07
    [count
    -0.07
    _Rect
    -0.06
    μήμα
    -0.06
    -set
    -0.06
    퓨
    -0.06
    recursive
    -0.06
    ंटर
    -0.06
     vyjád
    -0.06
     anticipation
    -0.06
    POSITIVE LOGITS
     winner
    0.06
     Sting
    0.06
     восстанов
    0.06
    _progress
    0.06
     Tribunal
    0.06
     polít
    0.06
     invited
    0.06
     [/
    0.06
     �
    0.06
     TO
    0.06
    Activations Density 0.027%

    No Known Activations