© 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
    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. 109253
    Prev
    Next
    INDEX
    Explanations

    difficulties

    np_max-act · gemini-2.0-flash

    This neuron detects emphasis-laden adjectives or adverbs (intensifiers) that signal importance or degree, such as “important,” “challenging,” “immense,” or “particularly.”

    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
    _dirs
    -0.07
    我们
    -0.07
    ovic
    -0.07
    الات
    -0.06
    enia
    -0.06
    .Object
    -0.06
    Coder
    -0.06
     intellectually
    -0.06
    -INFRINGEMENT
    -0.06
    (fragment
    -0.06
    POSITIVE LOGITS
     BrowserAnimationsModule
    0.06
     CVS
    0.06
     rozsah
    0.06
    ریه
    0.06
     گونه
    0.06
    .Active
    0.06
     QC
    0.06
     pracov
    0.06
    -flex
    0.06
     rf
    0.06
    Activations Density 0.228%

    No Known Activations