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. 27-RESID-POST-AA
    6. 102176
    Prev
    Next
    INDEX
    Explanations

    column

    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
     Royale
    -0.08
     whereby
    -0.07
     Thompson
    -0.07
    概
    -0.07
     Stokes
    -0.07
     thơm
    -0.07
    ภาพ
    -0.06
     west
    -0.06
     named
    -0.06
    。今
    -0.06
    POSITIVE LOGITS
     modest
    0.06
    _DRAW
    0.06
    		                       
    0.06
    .setMaximum
    0.06
     unwilling
    0.06
    ップ
    0.06
    ({...
    0.06
     गर
    0.06
     anmeld
    0.06
     jou
    0.06
    Activations Density 0.057%

    No Known Activations