© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 9014
    Prev
    Next
    INDEX
    Explanations

    chemical reactions

    np_max-act · gemini-2.0-flash

    words related to specific chemical compounds and their synthesis methods.

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

    The neuron flags numbered step markers (e.g. “1.”, “2.”, etc.) that introduce individual synthetic‐route steps.

    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
    pires
    -0.07
     ว
    -0.06
    iais
    -0.06
    _exact
    -0.06
     trouble
    -0.06
     Bristol
    -0.06
     ж
    -0.06
    _CBC
    -0.06
     Bridge
    -0.06
     franchises
    -0.06
    POSITIVE LOGITS
    _PRIVATE
    0.07
    ladatel
    0.07
    "It
    0.06
     وضعیت
    0.06
    例如
    0.06
     честь
    0.06
     PARAM
    0.06
    θηκε
    0.06
    جة
    0.06
     Федераль
    0.06
    Activations Density 0.029%

    No Known Activations