© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 12527
    Prev
    Next
    INDEX
    Explanations

    material

    np_max-act · gemini-2.0-flash

    The neuron specifically detects occurrences of the word “material.”

    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
    国
    -0.06
    ,,
    -0.06
    ')}}">↵
    -0.06
     Unique
    -0.06
     ulus
    -0.06
     witches
    -0.06
    аков
    -0.06
    --}}↵
    -0.06
    .NAME
    -0.06
     king
    -0.06
    POSITIVE LOGITS
     material
    0.10
     materiál
    0.09
     materia
    0.09
     materials
    0.09
     Mort
    0.09
     MATERIAL
    0.08
     материала
    0.08
     Material
    0.08
     coils
    0.07
    MRI
    0.07
    Activations Density 0.009%

    No Known Activations