© 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. 109402
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash

    This neuron specializes in spotting sequence‐transition cues (e.g. “After,” “end,” “completed,” commas marking a new step) in procedural or instructional text.

    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
    noun
    -0.07
     aquarium
    -0.07
    ~~
    -0.07
     Αρχ
    -0.06
    ��
    -0.06
     Nec
    -0.06
     demokrat
    -0.06
     UEFA
    -0.06
     Medicare
    -0.06
     Wood
    -0.06
    POSITIVE LOGITS
    WR
    0.06
     《
    0.06
     LINEAR
    0.06
     provocative
    0.06
    füg
    0.06
    ιστο
    0.06
     تسم
    0.06
    writing
    0.06
    _fr
    0.06
    _GR
    0.06
    Activations Density 0.066%

    No Known Activations