© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 109257
    Prev
    Next
    INDEX
    Explanations

    tangled

    np_max-act · gemini-2.0-flash

    The neuron responds to words evoking weaving or interlacing imagery (e.g. “interwoven,” “weaving,” “woven”).

    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
    (val
    -0.07
    δης
    -0.07
    _norm
    -0.07
    ё
    -0.06
    Army
    -0.06
    _scale
    -0.06
    ($"
    -0.06
     $"
    -0.06
    .TextAlign
    -0.06
     Soccer
    -0.06
    POSITIVE LOGITS
     tangled
    0.08
     intertwined
    0.07
     scrambled
    0.07
     Signup
    0.07
     overlapping
    0.06
     intertw
    0.06
    illow
    0.06
     woven
    0.06
     boundary
    0.06
     المل
    0.06
    Activations Density 0.022%

    No Known Activations