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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 43543
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash

    This neuron activates on named software or technology identifiers (library, framework, API, or product names and their acronyms).

    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
     год
    -0.07
    .&
    -0.07
     */↵
    -0.06
     Instance
    -0.06
     PE
    -0.06
     Islamabad
    -0.06
    су
    -0.06
     php
    -0.06
     PWM
    -0.06
     call
    -0.06
    POSITIVE LOGITS
     intermitt
    0.07
    contrib
    0.07
    lesh
    0.07
     حجم
    0.06
    Stars
    0.06
    ?option
    0.06
    ís
    0.06
    (typeof
    0.06
     Florian
    0.06
    няя
    0.06
    Activations Density 0.066%

    No Known Activations