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. 7-RESID-POST-AA
    6. 109427
    Prev
    Next
    INDEX
    Explanations

    Questions/Answers/Symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    уру
    -0.07
    '))->
    -0.07
    就
    -0.06
     janvier
    -0.06
     市
    -0.06
    VA
    -0.06
    Im
    -0.06
     Frankfurt
    -0.06
    794
    -0.06
     сез
    -0.06
    POSITIVE LOGITS
     CONSTANTS
    0.07
    .DataBind
    0.07
    _CAM
    0.06
    OTE
    0.06
     Totally
    0.06
     rend
    0.06
    ué
    0.06
    elight
    0.06
    ebin
    0.06
     moderation
    0.06
    Activations Density 0.097%

    No Known Activations