© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 109681
    Prev
    Next
    INDEX
    Explanations

    -----

    np_max-act · gemini-2.0-flash

    The neuron identifies structural email header/footer markers (like “-----” separators and fields such as “From:”, “Subject:”, “Original Message”, 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
    );↵↵↵
    -0.07
    {@
    -0.07
    viewer
    -0.07
     fmt
    -0.07
    .gif
    -0.06
     barric
    -0.06
    掌
    -0.06
     законодавства
    -0.06
    methodPointerType
    -0.06
    >&
    -0.06
    POSITIVE LOGITS
     decor
    0.06
     yelling
    0.06
     caus
    0.06
     "<?
    0.06
    _lng
    0.06
    	unset
    0.06
    (mail
    0.06
     <?=
    0.06
     specializing
    0.06
     инвести
    0.06
    Activations Density 0.006%

    No Known Activations