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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 27-RESID-POST-AA
    11. 104123
    Prev
    Next
    INDEX
    Explanations

    HTTP error codes

    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_27/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    \Factory
    -0.07
     concede
    -0.07
    :")↵
    -0.07
     …↵↵
    -0.07
     woes
    -0.07
     implants
    -0.07
     대학
    -0.07
     pointer
    -0.06
    ())),↵
    -0.06
     cylinder
    -0.06
    POSITIVE LOGITS
    країн
    0.07
    ım
    0.06
     Pix
    0.06
    ा�
    0.06
    asse
    0.06
     만
    0.06
     MMA
    0.06
     Lamb
    0.06
    _period
    0.05
    interp
    0.05
    Activations Density 0.025%

    No Known Activations