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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 41103
    Prev
    Next
    INDEX
    Explanations

    only

    np_max-act · gemini-2.0-flash

    The neuron activates on common content words (subword pieces of verbs and pronouns like “contemn,” “what,” “he,” “give”) rather than on punctuation or formatting tokens.

    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
    紅
    -0.07
    _POOL
    -0.06
     配
    -0.06
     hammer
    -0.06
     pigeon
    -0.06
     PROF
    -0.06
     poetic
    -0.06
     flavorful
    -0.06
     crisp
    -0.06
     Auburn
    -0.06
    POSITIVE LOGITS
    jab
    0.07
    зи
    0.07
    ính
    0.07
    倫
    0.07
    erek
    0.07
    rbrace
    0.07
    Writer
    0.06
    shire
    0.06
    |\
    0.06
    mania
    0.06
    Activations Density 0.000%

    No Known Activations