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. 11-RESID-POST-AA
    6. 75416
    Prev
    Next
    INDEX
    Explanations

    Software development/bugs

    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
    开始
    -0.07
     installation
    -0.07
     ter
    -0.06
     toàn
    -0.06
    PP
    -0.06
    来た
    -0.06
    _current
    -0.06
    _ping
    -0.06
     bert
    -0.06
     overload
    -0.06
    POSITIVE LOGITS
     Walking
    0.06
    うん
    0.06
    _information
    0.06
    WillDisappear
    0.06
    ('<?
    0.06
     slou
    0.06
    thalm
    0.06
     Keeping
    0.06
     borough
    0.06
    	freopen
    0.06
    Activations Density 0.146%

    No Known Activations