© 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. 92187
    Prev
    Next
    INDEX
    Explanations

    relates

    np_max-act · gemini-2.0-flash

    The neuron detects floating‐point numeric literals (decimal numbers) 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
     Gill
    -0.07
     ils
    -0.07
    _EXPRESSION
    -0.07
    atted
    -0.06
    _COLS
    -0.06
     Compatibility
    -0.06
     Crist
    -0.06
    ng
    -0.06
     Forg
    -0.06
     مرگ
    -0.06
    POSITIVE LOGITS
     Goal
    0.06
     advisable
    0.06
     حم
    0.06
    532
    0.06
    ΗΝ
    0.06
    ilere
    0.06
    _common
    0.06
    ;;;
    0.06
     permanently
    0.06
     programme
    0.06
    Activations Density 0.005%

    No Known Activations