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. 53833
    Prev
    Next
    INDEX
    Explanations

    line

    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
    adı
    -0.06
     adds
    -0.06
     zeros
    -0.06
     Cape
    -0.06
     конструкции
    -0.06
     mansion
    -0.06
    Manifest
    -0.05
     reminiscent
    -0.05
     �
    -0.05
    zych
    -0.05
    POSITIVE LOGITS
    >:
    0.07
     screened
    0.07
    	LL
    0.07
     herbs
    0.07
     Перв
    0.06
     tráv
    0.06
    /kubernetes
    0.06
    ughter
    0.06
    (screen
    0.06
     siden
    0.06
    Activations Density 0.000%

    No Known Activations