© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 59245
    Prev
    Next
    INDEX
    Explanations

    commas

    np_max-act · gemini-2.0-flash

    The neuron responds to ornate descriptive modifiers—particularly lofty adjectives (e.g. “magnificent”) and formal concessive adverbs (e.g. “albeit”).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    izzy
    -0.07
    }/>
    -0.07
    Ltd
    -0.07
     سیم
    -0.06
    _De
    -0.06
     března
    -0.06
    779
    -0.06
    _Al
    -0.06
    .Sleep
    -0.06
    슈
    -0.06
    POSITIVE LOGITS
     trainable
    0.07
    	typedef
    0.07
    YG
    0.06
    その
    0.06
    0.06
    ulos
    0.06
    _splits
    0.06
     edeb
    0.06
    [w
    0.06
    (duration
    0.06
    Activations Density 0.023%

    No Known Activations