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

    Neuronpedia

    APICircuit 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. 11-RESID-POST-AA
    6. 81366
    Prev
    Next
    INDEX
    Explanations

    sand

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of automotive body‐filling and sanding materials or actions (e.g. Bondo/putty and sandpaper/sanding).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     techn
    -0.06
     kỹ
    -0.06
     slav
    -0.06
    Bulk
    -0.06
     сьогодні
    -0.06
    ultimo
    -0.06
     They
    -0.06
     Apartment
    -0.06
     Techniques
    -0.06
     Nate
    -0.06
    POSITIVE LOGITS
    343
    0.07
     Corpor
    0.06
    력이
    0.06
     kickoff
    0.06
    aland
    0.06
    344
    0.06
     financ
    0.06
    COVERY
    0.06
    amphetamine
    0.06
     日本
    0.06
    Activations Density 0.008%

    No Known Activations