© 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. 23076
    Prev
    Next
    INDEX
    Explanations

    Fitness

    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
     kro
    -0.07
    imbabwe
    -0.07
    нії
    -0.07
    uj
    -0.07
     devices
    -0.06
    젠
    -0.06
    Gro
    -0.06
    eyJ
    -0.06
    κού
    -0.06
    cx
    -0.06
    POSITIVE LOGITS
    AppName
    0.06
    .Collapsed
    0.06
    饮
    0.06
    	pp
    0.06
    +'\
    0.06
    signature
    0.06
    ��
    0.06
    }->{
    0.06
     superiority
    0.06
     Singer
    0.06
    Activations Density 0.036%

    No Known Activations