Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 110752
    Prev
    Next
    INDEX
    Explanations

    on

    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
    icional
    -0.07
     nieuwe
    -0.06
     대답
    -0.06
    択
    -0.06
     Yus
    -0.06
     ridden
    -0.06
    	report
    -0.06
     Cycl
    -0.06
    INF
    -0.06
     racked
    -0.06
    POSITIVE LOGITS
    joining
    0.06
    _PID
    0.06
    '>"+
    0.06
    :both
    0.06
    pushViewController
    0.06
     computed
    0.06
    alen
    0.06
    ynchronized
    0.06
     Açık
    0.06
     Т
    0.06
    Activations Density 0.012%

    No Known Activations