© 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 (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 43450
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric literals (especially floating‐point numbers and other digit sequences) in the text.

    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
     Cont
    -0.06
     Σ
    -0.06
     relatively
    -0.06
    discussion
    -0.06
     stream
    -0.06
    _BINDING
    -0.06
    닥
    -0.06
    Recorder
    -0.06
     سنگ
    -0.06
    บรร
    -0.06
    POSITIVE LOGITS
     standards
    0.07
     ألمان
    0.07
     SPA
    0.06
    -comp
    0.06
     Surgery
    0.06
    AREN
    0.06
    -du
    0.06
     diagnosis
    0.06
     abilities
    0.06
     wifi
    0.06
    Activations Density 0.030%

    No Known Activations