Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 86314
    Prev
    Next
    INDEX
    Explanations

    that

    np_max-act · gemini-2.0-flash

    The neuron is sensitive to numeric expressions—especially numbers, decimals, and percentage‐style values.

    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
    809
    -0.07
     misplaced
    -0.07
    sequent
    -0.06
    BH
    -0.06
     attentive
    -0.06
     explanatory
    -0.06
     lizard
    -0.06
     tempo
    -0.06
     Mez
    -0.06
    Certainly
    -0.06
    POSITIVE LOGITS
     최대
    0.07
    _adjust
    0.07
    虽
    0.07
    人気
    0.06
     dahi
    0.06
    LayoutManager
    0.06
     additionally
    0.06
     �
    0.06
    WithDuration
    0.06
    **
    0.06
    Activations Density 0.869%

    No Known Activations