© 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. 93925
    Prev
    Next
    INDEX
    Explanations

    ni

    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
     upto
    -0.07
    	push
    -0.06
    rav
    -0.06
     revealing
    -0.06
    рій
    -0.06
    orph
    -0.06
    .DAY
    -0.06
    fef
    -0.06
    .flat
    -0.06
    oooo
    -0.06
    POSITIVE LOGITS
     Omni
    0.15
     errno
    0.12
    ni
    0.10
    errno
    0.09
    aden
    0.08
     Baton
    0.07
    죠
    0.07
    .“↵↵
    0.06
     Nicola
    0.06
    キュ
    0.06
    Activations Density 0.004%

    No Known Activations