© 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. 15-RESID-POST-AA
    11. 93316
    Prev
    Next
    INDEX
    Explanations

    uja

    np_max-act · gemini-2.0-flash

    strings of uppercase-letter or mixed-case all-caps tokens (e.g., acronyms or base64-like chunks / encoded data)

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    [f
    -0.07
     й
    -0.06
    继
    -0.06
     thought
    -0.06
    ました
    -0.06
     Roch
    -0.06
     ster
    -0.06
     Questions
    -0.06
     Closed
    -0.06
    �
    -0.06
    POSITIVE LOGITS
    a
    0.15
    ca
    0.14
    ra
    0.14
    pa
    0.14
    ha
    0.13
    ka
    0.13
    ula
    0.13
    RA
    0.13
    ta
    0.13
    CA
    0.12
    Activations Density 0.951%

    No Known Activations