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. 19-RESID-POST-AA
    6. 9833
    Prev
    Next
    INDEX
    Explanations

    and

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    hevik
    -0.06
     Vander
    -0.06
    Número
    -0.06
     Гри
    -0.06
    .verbose
    -0.06
    groupid
    -0.06
    fasta
    -0.06
     боли
    -0.06
     gele
    -0.06
    _BS
    -0.06
    POSITIVE LOGITS
    	end
    0.07
     platinum
    0.07
     swept
    0.06
    _ack
    0.06
     kat
    0.06
     Proposed
    0.06
    되었다
    0.06
     occas
    0.06
     battleground
    0.06
     undert
    0.06
    Activations Density 0.000%

    No Known Activations