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. 23-RESID-POST-AA
    6. 40613
    Prev
    Next
    INDEX
    Explanations

    properly

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     جهان
    -0.06
    more
    -0.06
     arrays
    -0.06
     aggregate
    -0.06
     fictional
    -0.06
    -FIRST
    -0.06
    Document
    -0.06
    hours
    -0.06
    (Message
    -0.06
     همه
    -0.06
    POSITIVE LOGITS
    ذلك
    0.07
    )!↵
    0.06
     IDisposable
    0.06
     vigorous
    0.06
    ーデ
    0.06
    _dis
    0.06
    预
    0.06
    bbb
    0.06
    			
    ↵			
    ↵
    0.06
    .expect
    0.06
    Activations Density 0.045%

    No Known Activations