© 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. 822
    Prev
    Next
    INDEX
    Explanations

    forms

    np_max-act · gemini-2.0-flash

    This neuron activates on occurrences of the word “forms” (as in “binary forms,”) in license header 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
     هج
    -0.07
    .AddSingleton
    -0.07
    aft
    -0.07
    [];
↵
    -0.07
     txt
    -0.06
    BREAK
    -0.06
    zyć
    -0.06
    .accuracy
    -0.06
     Casting
    -0.06
    วด
    -0.06
    POSITIVE LOGITS
     VL
    0.07
    uggested
    0.07
    )>↵
    0.06
     ΕΛ
    0.06
     assignments
    0.06
     kid
    0.06
    GLOBALS
    0.06
    fulness
    0.06
     firms
    0.06
    670
    0.06
    Activations Density 0.000%

    No Known Activations