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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 5984
    Prev
    Next
    INDEX
    Explanations

    o

    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
     설치
    -0.08
     coer
    -0.07
     JW
    -0.07
    ROWN
    -0.07
     Lust
    -0.07
     Beg
    -0.06
    locs
    -0.06
     codec
    -0.06
    tep
    -0.06
    oref
    -0.06
    POSITIVE LOGITS
     affirmation
    0.07
     yAxis
    0.06
     ventana
    0.06
    	vector
    0.06
     än
    0.06
     vacation
    0.06
    _PROFILE
    0.06
    //---------------------------------------------------------------------------↵
    0.06
     localObject
    0.06
    Ms
    0.05
    Activations Density 0.000%

    No Known Activations