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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 12392
    Prev
    Next
    INDEX
    Explanations

    say 'ending with a cyrillic ending'

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sty
    -0.07
     prohib
    -0.07
     ]);↵↵
    -0.06
     Signal
    -0.06
     inhibition
    -0.06
     endorse
    -0.06
     passage
    -0.06
    VR
    -0.06
    _PRESENT
    -0.06
     Friendship
    -0.06
    POSITIVE LOGITS
    อห
    0.07
    เอง
    0.06
    ευ
    0.06
    voř
    0.06
     експ
    0.06
     المغ
    0.06
     Graham
    0.06
    _RS
    0.06
    .life
    0.06
    Щ
    0.06
    Activations Density 0.002%

    No Known Activations