© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 103963
    Prev
    Next
    INDEX
    Explanations

    "."

    np_max-act · gemini-2.0-flash

    The neuron is highly activated by punctuation delimiters—especially periods, commas (and similar separators like slashes) that mark clause, sentence, or list boundaries.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    discussions about sex and relationships.

    oai_token-act-pair · gpt-4o-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
     奥
    -0.07
    .Icon
    -0.07
    16
    -0.06
    字段
    -0.06
    Servers
    -0.06
    .one
    -0.06
     số
    -0.06
    Conf
    -0.06
    ('').
    -0.06
    TH
    -0.06
    POSITIVE LOGITS
     Σεπ
    0.07
    .getMap
    0.06
    　ノ
    0.06
     leveraging
    0.06
    аторы
    0.06
    %p
    0.06
     ты
    0.06
    _AUT
    0.06
     jt
    0.06
     öğret
    0.06
    Activations Density 0.027%

    No Known Activations