© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 43280
    Prev
    Next
    INDEX
    Explanations

    change

    np_max-act · gemini-2.0-flash

    The neuron fires on verbs that denote modifications or quantitative changes (e.g. “changed,” “added,” “increased,” “shortened,” “upgraded,” etc.).

    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
     ConcurrentHashMap
    -0.07
    -dis
    -0.06
     grid
    -0.06
     cez
    -0.06
    �
    -0.06
    .SC
    -0.06
     vznik
    -0.06
     parentId
    -0.06
    toc
    -0.06
    .gz
    -0.06
    POSITIVE LOGITS
     remain
    0.07
     template
    0.07
    uale
    0.07
     Manson
    0.07
    wins
    0.07
    bose
    0.06
    __↵
    0.06
     Baylor
    0.06
    good
    0.06
    ої
    0.06
    Activations Density 0.062%

    No Known Activations