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. 40640
    Prev
    Next
    INDEX
    Explanations

    prompts

    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
     málo
    -0.07
    -wh
    -0.07
    Anyone
    -0.07
    -tw
    -0.07
    ança
    -0.06
     stressful
    -0.06
    íně
    -0.06
    lineEdit
    -0.06
    ANCE
    -0.06
    ẵ
    -0.06
    POSITIVE LOGITS
    ErrorMsg
    0.07
    Env
    0.07
     Metadata
    0.07
     Res
    0.07
    .ad
    0.06
     Lambda
    0.06
     اجتماع
    0.06
    .Seek
    0.06
    ilk
    0.06
     neutr
    0.06
    Activations Density 0.129%

    No Known Activations