© 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. 126350
    Prev
    Next
    INDEX
    Explanations

    lines

    np_max-act · gemini-2.0-flash

    The neuron selectively activates on longer content words—especially multi-syllable or technical terms—rather than short function words.

    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
     Mines
    -0.06
     specially
    -0.06
    _memory
    -0.06
    _malloc
    -0.06
     خورد
    -0.06
     Kitt
    -0.06
     حکوم
    -0.06
     Sammy
    -0.06
    ”—
    -0.06
     menus
    -0.06
    POSITIVE LOGITS
     advis
    0.07
     technik
    0.07
    _typ
    0.07
    Rule
    0.07
    kode
    0.07
     अ
    0.07
     testData
    0.07
    无
    0.07
     Müslüman
    0.07
     hazır
    0.06
    Activations Density 0.874%

    No Known Activations