© 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. 15-RESID-POST-AA
    11. 39798
    Prev
    Next
    INDEX
    Explanations

    sentence fragments

    np_max-act · gemini-2.0-flash

    the neuron highlights content-bearing words (important nouns, verbs, and topic-related terms) in a passage.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     setHidden
    -0.07
     форме
    -0.07
    �
    -0.06
     Lithuania
    -0.06
    âl
    -0.06
     apenas
    -0.06
    shouldReceive
    -0.06
     často
    -0.06
    &)↵
    -0.06
    elm
    -0.06
    POSITIVE LOGITS
     sluggish
    0.07
    관리자
    0.07
     clipped
    0.06
    _hyper
    0.06
    .open
    0.06
    aksi
    0.06
    orious
    0.06
     Rac
    0.06
     bargaining
    0.06
    UIS
    0.06
    Activations Density 0.786%

    No Known Activations