© 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. 91735
    Prev
    Next
    INDEX
    Explanations

    place

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of “in-place” operations (e.g., in‐place sorting).

    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
    _groups
    -0.06
    -stat
    -0.06
    NC
    -0.06
     wicht
    -0.06
    TimeZone
    -0.06
     Simpl
    -0.06
     redirects
    -0.06
     MDMA
    -0.06
     ước
    -0.05
    _theta
    -0.05
    POSITIVE LOGITS
    Mutable
    0.07
     پژوه
    0.06
     Dave
    0.06
    park
    0.06
     花
    0.06
     People
    0.06
     خواهد
    0.06
    //=
    0.06
     Initialize
    0.06
    UIApplicationDelegate
    0.06
    Activations Density 0.002%

    No Known Activations