© 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. 19-RESID-POST-AA
    11. 73395
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    mentions of numeric formats, digit sequences, and numeric-range specifications (e.g., routing/account number formats, temperature ranges, or numeric field values).

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31

    function words

    np_max-act · gpt-5-miniTriggered by @yooniel31
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ‌
    -0.07
    rpm
    -0.06
     PERMISSION
    -0.06
     models
    -0.06
     BUY
    -0.06
    _ADDRESS
    -0.06
    атем
    -0.06
    -law
    -0.06
     Mét
    -0.06
    	light
    -0.06
    POSITIVE LOGITS
    .</
    0.06
     нанес
    0.06
    lerdi
    0.06
    _monitor
    0.06
    і
    0.06
    ).[
    0.06
    ']).
    0.06
     olduk
    0.05
     pictureBox
    0.05
    .[
    0.05
    Activations Density 0.892%

    No Known Activations