Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 40709
    Prev
    Next
    INDEX
    Explanations

    business services

    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
     Miller
    -0.07
    .Date
    -0.06
     productive
    -0.06
    _gem
    -0.06
    HasForeignKey
    -0.06
     Shame
    -0.06
    ForMember
    -0.06
    _square
    -0.06
    	password
    -0.06
    帖
    -0.06
    POSITIVE LOGITS
    -pills
    0.07
    Produ
    0.07
    .equ
    0.06
     synergy
    0.06
     woes
    0.06
    AREST
    0.06
    FUNCTION
    0.06
    getToken
    0.06
    ynth
    0.06
     redistrib
    0.06
    Activations Density 0.205%

    No Known Activations