© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 29944
    Prev
    Next
    INDEX
    Explanations

    political statements

    np_max-act · gemini-2.0-flash

    This neuron activates on dateline and headline–style elements in news or press‐release text, i.e. tokens marking dates, places, publication locations, and official names.

    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
    Chip
    -0.07
    _CLIP
    -0.07
     Ctrl
    -0.07
     orbs
    -0.06
    ο
    -0.06
     treasure
    -0.06
     tiện
    -0.06
     sel
    -0.06
     Ironically
    -0.06
    ità
    -0.06
    POSITIVE LOGITS
     住
    0.06
     DirectoryInfo
    0.06
    _FINE
    0.06
     PIL
    0.06
     NONINFRINGEMENT
    0.06
     getSupportFragmentManager
    0.06
    BOSE
    0.06
     kháng
    0.06
    ادات
    0.06
    /*@
    0.06
    Activations Density 0.105%

    No Known Activations