© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 91700
    Prev
    Next
    INDEX
    Explanations

    church

    np_max-act · gemini-2.0-flash

    The neuron responds to mentions of church or cathedral buildings (e.g., the words “church,” “Cathedral,” “Parish,” etc.).

    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
     cursos
    -0.07
    排名
    -0.07
    .NotNull
    -0.06
     مؤ
    -0.06
     Gaines
    -0.06
     modne
    -0.06
     runner
    -0.06
    dej
    -0.06
     PAC
    -0.06
     خارج
    -0.06
    POSITIVE LOGITS
    ευ
    0.07
    �
    0.07
    ?id
    0.06
     Firearms
    0.06
    ;top
    0.06
    built
    0.06
    noxious
    0.06
    -thumb
    0.06
     podmín
    0.06
    足球
    0.06
    Activations Density 0.030%

    No Known Activations