© 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. 25346
    Prev
    Next
    INDEX
    Explanations

    .

    np_max-act · gemini-2.0-flash

    information about communication and customer service policies.

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

    The main thing this neuron does is detect sentence-ending punctuation and the tokens immediately surrounding the ends 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
    Der
    -0.07
     subscription
    -0.07
    .song
    -0.06
    .estado
    -0.06
     Merr
    -0.06
     fluffy
    -0.06
    (exit
    -0.06
    .visitMethod
    -0.06
    _drop
    -0.06
    _demand
    -0.06
    POSITIVE LOGITS
    .HashMap
    0.07
    _superuser
    0.06
     empower
    0.06
    inger
    0.06
     Hành
    0.06
    —even
    0.06
     ambiguous
    0.06
    Ά
    0.06
     children
    0.06
    ??
    0.06
    Activations Density 0.055%

    No Known Activations