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. 86062
    Prev
    Next
    INDEX
    Explanations

    expand

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of expanded or re-released album editions (e.g. “expanded version,” “additional songs,” “stereo version,” etc.).

    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
     heed
    -0.08
    oves
    -0.06
     amen
    -0.06
    -cut
    -0.06
    _cut
    -0.06
    408
    -0.06
     根
    -0.06
    -*
    -0.06
     incess
    -0.06
    ellij
    -0.06
    POSITIVE LOGITS
     Panda
    0.07
    (File
    0.06
    Highlighted
    0.06
     Wrapper
    0.06
     glowing
    0.06
     mein
    0.06
    国际
    0.06
    -elected
    0.06
    unge
    0.06
    Foot
    0.06
    Activations Density 0.044%

    No Known Activations