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. 130630
    Prev
    Next
    INDEX
    Explanations

    proof

    np_max-act · gemini-2.0-flash

    The neuron activates on words in “-proof” or “proof” compounds (e.g. foolproof, bulletproof, fail-proof).

    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
     birlikte
    -0.06
    Compar
    -0.06
     lässt
    -0.06
                
    -0.06
     ecosystem
    -0.06
    这样的
    -0.06
    .LA
    -0.06
     hott
    -0.06
    Logo
    -0.06
     tiener
    -0.06
    POSITIVE LOGITS
     Bought
    0.08
     Fang
    0.07
    orton
    0.07
    usted
    0.07
    voir
    0.07
     зараз
    0.07
    "]->
    0.06
     FRIEND
    0.06
    뢰
    0.06
     assured
    0.06
    Activations Density 0.005%

    No Known Activations