© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RESID-POST-AA
    11. 42799
    Prev
    Next
    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash

    It detects utterances that open with an apologetic introductory phrase (an apology at the start of a post).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pelosi
    -0.06
    気
    -0.06
     propri
    -0.06
     perception
    -0.06
    ح
    -0.06
     �
    -0.06
     Pais
    -0.06
     sitio
    -0.06
     conversions
    -0.06
    woord
    -0.06
    POSITIVE LOGITS
     měly
    0.07
    )?;↵↵
    0.07
    _lng
    0.07
    OMUX
    0.06
     cinsel
    0.06
    _REMOVE
    0.06
    =h
    0.06
     Diğer
    0.06
    .Windows
    0.06
     Král
    0.06
    Activations Density 0.005%

    No Known Activations