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. 130708
    Prev
    Next
    INDEX
    Explanations

    IR

    np_max-act · gemini-2.0-flash

    The neuron fires on the substring “IR” in legal citation lines—specifically on the “CIR” in circuit‐court references.

    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
    -dom
    -0.07
    을
    -0.07
     MongoDB
    -0.07
     sol
    -0.06
     eclipse
    -0.06
     Parenthood
    -0.06
     gefunden
    -0.06
     *)&
    -0.06
    Pane
    -0.06
     Zend
    -0.06
    POSITIVE LOGITS
     }},↵
    0.08
    \",↵
    0.08
     Offset
    0.06
     algumas
    0.06
     Chevron
    0.06
     abrasive
    0.06
    鎮
    0.06
     miejsc
    0.06
    /contentassist
    0.06
     trí
    0.06
    Activations Density 0.000%

    No Known Activations