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. 15-RESID-POST-AA
    6. 73810
    Prev
    Next
    INDEX
    Explanations

    ome

    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
     appl
    -0.07
    	opt
    -0.07
     ссыл
    -0.06
    _var
    -0.06
    .char
    -0.06
     Lar
    -0.06
     clay
    -0.06
    straint
    -0.06
     gestures
    -0.06
    .addr
    -0.06
    POSITIVE LOGITS
     Genome
    0.09
     genome
    0.07
     genomes
    0.07
    ummy
    0.07
     abdom
    0.07
    -MM
    0.07
    OMEM
    0.07
    れて
    0.07
    мом
    0.07
    �ng
    0.06
    Activations Density 0.007%

    No Known Activations