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. 110738
    Prev
    Next
    INDEX
    Explanations

    Years and locations

    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
    	DEBUG
    -0.07
    carousel
    -0.07
    318
    -0.07
    işleri
    -0.06
    ิน
    -0.06
    maker
    -0.06
     있
    -0.06
    302
    -0.06
    BIG
    -0.06
    ]+\
    -0.06
    POSITIVE LOGITS
    ![
    0.06
    trecht
    0.06
    مو
    0.06
    ansa
    0.06
     weap
    0.06
    会社
    0.06
     forControlEvents
    0.06
    Anc
    0.06
     apare
    0.06
    _office
    0.06
    Activations Density 0.006%

    No Known Activations