© 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 (Instruct)
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 92139
    Prev
    Next
    INDEX
    Explanations

    relating

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     downtown
    -0.07
    	switch
    -0.07
     guarded
    -0.07
     expected
    -0.06
     Spawn
    -0.06
     Lưu
    -0.06
     piano
    -0.06
     creek
    -0.06
    .Special
    -0.06
     incoming
    -0.06
    POSITIVE LOGITS
    �
    0.07
     relating
    0.07
    (template
    0.06
    391
    0.06
    (touch
    0.06
    ５
    0.06
    stay
    0.06
    EMU
    0.06
    (term
    0.06
    interpre
    0.06
    Activations Density 0.005%

    No Known Activations