© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 55848
    Prev
    Next
    INDEX
    Explanations

    image credits/references

    np_max-act · gemini-2.0-flash

    The neuron detects image credit or photo‐attribution segments (e.g. “Photo: … Credit: …”).

    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
     Over
    -0.06
    ٥
    -0.06
     goalkeeper
    -0.06
    nnen
    -0.06
    دو
    -0.06
    .getChannel
    -0.06
    entimes
    -0.06
    /output
    -0.06
     Seit
    -0.06
    _total
    -0.06
    POSITIVE LOGITS
     جه
    0.07
    按钮
    0.06
     fid
    0.06
    利
    0.06
    ']))
    0.06
     saç
    0.06
     iniciar
    0.06
    0.06
     νο
    0.06
    rası
    0.05
    Activations Density 0.010%

    No Known Activations