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. 130289
    Prev
    Next
    INDEX
    Explanations

    e.g

    np_max-act · gemini-2.0-flash

    The neuron activates on decimal-formatted numeric values (i.e. floating-point numbers often shown as example 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
    она
    -0.07
    迅
    -0.07
    questions
    -0.07
    BitFields
    -0.07
    Interactive
    -0.07
    Berry
    -0.07
    脂
    -0.07
    ्यत
    -0.07
    ира
    -0.06
    534
    -0.06
    POSITIVE LOGITS
    .g
    0.10
     irgend
    0.08
     de
    0.07
     eg
    0.07
     d
    0.07
     Cay
    0.07
     Gold
    0.07
     свого
    0.06
    —for
    0.06
    .Web
    0.06
    Activations Density 0.018%

    No Known Activations