© 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. 12553
    Prev
    Next
    INDEX
    Explanations

    contractions and "is"

    np_max-act · gemini-2.0-flash

    The neuron fires on informal, first-person status-update openings—especially “Well, it’s been a …” style phrases.

    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
    _Manager
    -0.07
     contempl
    -0.07
    807
    -0.07
     herbal
    -0.06
     shoe
    -0.06
     coating
    -0.06
    しま
    -0.06
     Armen
    -0.06
    =subprocess
    -0.06
     Ấ
    -0.06
    POSITIVE LOGITS
    Parent
    0.07
    scriptId
    0.07
    níka
    0.06
     малень
    0.06
    名
    0.06
    .readlines
    0.06
    Amazing
    0.06
     poměr
    0.06
     cambi
    0.06
     التي
    0.06
    Activations Density 0.033%

    No Known Activations