© 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. 13488
    Prev
    Next
    INDEX
    Explanations

    Orientation and direction

    np_max-act · gemini-2.0-flash

    This neuron activates on words specifying the orientation or facing direction of an object (e.g., “facing,” “pointing,” “upward,” “downward”).

    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
    lica
    -0.07
     tỏ
    -0.07
    ову
    -0.07
    -fit
    -0.06
    "},↵
    -0.06
    	Description
    -0.06
     dirty
    -0.06
    국의
    -0.06
    ิญญ
    -0.06
    .GET
    -0.06
    POSITIVE LOGITS
     Qualcomm
    0.06
     buttonWithType
    0.06
    袋
    0.06
     errorCallback
    0.06
     staggering
    0.06
    @Json
    0.06
     Mandela
    0.06
     اتفاق
    0.06
    的情
    0.06
    _pg
    0.06
    Activations Density 0.006%

    No Known Activations