© 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 EvalsExportsinterp-engineNEWAPI 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. 102066
    Prev
    Next
    INDEX
    Explanations

    pronouns

    np_max-act · gemini-2.0-flash

    descriptions of dominant and possessive relationships.

    oai_token-act-pair · gpt-4o-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
    .LogWarning
    -0.07
    IMPLEMENT
    -0.07
    mask
    -0.07
    alah
    -0.07
     compliant
    -0.06
    Console
    -0.06
    teams
    -0.06
     structs
    -0.06
     接
    -0.06
    AMED
    -0.06
    POSITIVE LOGITS
     Transitional
    0.07
     injury
    0.06
    лав
    0.06
    _roles
    0.06
     mí
    0.06
     vole
    0.06
    状況
    0.06
     enlarge
    0.06
    icone
    0.05
     Budapest
    0.05
    Activations Density 0.020%

    No Known Activations