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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 7-RESID-POST-AA
    11. 46356
    Prev
    Next
    INDEX
    Explanations

    fear

    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
     možná
    -0.07
     他
    -0.06
    '})↵↵
    -0.06
     söyley
    -0.06
     重
    -0.06
        
↵
↵
    -0.06
     shortcuts
    -0.06
     Producer
    -0.06
    19
    -0.06
    ()
↵
↵
↵
    -0.06
    POSITIVE LOGITS
     frightening
    0.06
    _"
    0.06
    TagName
    0.06
     krb
    0.06
    art
    0.06
    _static
    0.06
     terrifying
    0.06
    ुट
    0.06
    -ticket
    0.06
    .addObject
    0.06
    Activations Density 0.114%

    No Known Activations