© 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. 11-RESID-POST-AA
    11. 52869
    Prev
    Next
    INDEX
    Explanations

    Stripping code/text

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    part
    -0.07
     Signup
    -0.07
     ساز
    -0.07
    recogn
    -0.06
    .EqualTo
    -0.06
     userList
    -0.06
    timeout
    -0.06
     Alison
    -0.06
    down
    -0.06
     laying
    -0.06
    POSITIVE LOGITS
    处
    0.07
    ?,
    0.07
     unbelievable
    0.07
    ----------------------------
    0.06
     Edited
    0.06
    ?:
    0.06
     Immediately
    0.06
     bě
    0.06
    	BYTE
    0.06
    Я
    0.06
    Activations Density 0.031%

    No Known Activations