© 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. 57188
    Prev
    Next
    INDEX
    Explanations

    camera

    np_max-act · gemini-2.0-flash

    The neuron activates on words describing photographic composition details—especially camera references (e.g. camera, lens, framing, “looking into the camera”).

    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
     births
    -0.06
    번
    -0.06
    .cvtColor
    -0.06
     EXEMPLARY
    -0.06
     contemplating
    -0.06
    Generally
    -0.06
    ủ
    -0.06
     Dix
    -0.06
     Gmail
    -0.06
     딸
    -0.06
    POSITIVE LOGITS
     &,
    0.07
    _FINISH
    0.07
     campaigned
    0.07
     STR
    0.06
     Perf
    0.06
    //================================================================
    0.06
     Josef
    0.06
    [...,
    0.06
    ∏
    0.06
    -ie
    0.06
    Activations Density 0.009%

    No Known Activations