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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3-RESID-POST-AA
    11. 121698
    Prev
    Next
    INDEX
    Explanations

    also

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     uomo
    -0.06
     newArray
    -0.06
    (key
    -0.06
    .Tipo
    -0.06
    	try
    -0.06
    Screens
    -0.06
     cost
    -0.06
    Facing
    -0.06
     productId
    -0.06
    Movie
    -0.06
    POSITIVE LOGITS
     also
    0.13
     také
    0.09
     ALSO
    0.09
     también
    0.08
     aussi
    0.08
     также
    0.08
    也是
    0.08
     Lafayette
    0.07
     Also
    0.07
     Alg
    0.07
    Activations Density 0.099%

    No Known Activations