© 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. 43366
    Prev
    Next
    INDEX
    Explanations

    advice

    np_max-act · gemini-2.0-flash

    instructions for training behaviors in dogs.

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

    The neuron detects structural formatting tokens that denote list items or section boundaries (e.g., step numbers, bullets, and header markers).

    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
    fragistics
    -0.07
     Tibetan
    -0.07
    Ele
    -0.06
     navCtrl
    -0.06
     obj
    -0.06
     Zionist
    -0.06
    lify
    -0.06
     önceki
    -0.06
    jual
    -0.06
    .opendaylight
    -0.06
    POSITIVE LOGITS
     refurbished
    0.07
    AILY
    0.07
     adequately
    0.06
     Won
    0.06
     �
    0.06
    mouth
    0.06
    Bright
    0.06
     rocked
    0.06
     sesso
    0.06
    :max
    0.06
    Activations Density 0.026%

    No Known Activations