© 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. 639
    Prev
    Next
    INDEX
    Explanations

    Period

    np_max-act · gemini-2.0-flash

    The neuron primarily responds to sentence-ending punctuation (i.e. tokens marking the end of sentences).

    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
     مخصوص
    -0.06
    _Equals
    -0.06
    -pop
    -0.06
     glucose
    -0.06
     output
    -0.06
     gears
    -0.06
     outputs
    -0.06
    ise
    -0.06
    _role
    -0.06
    erm
    -0.06
    POSITIVE LOGITS
    Mem
    0.07
     memorable
    0.06
    (())↵
    0.06
    ุมชน
    0.06
    .Mockito
    0.06
     USED
    0.06
     evaluates
    0.06
    roj
    0.06
    πέ
    0.06
    /.
    0.06
    Activations Density 0.138%

    No Known Activations