© 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. 13129
    Prev
    Next
    INDEX
    Explanations

    apparently

    np_max-act · gemini-2.0-flash

    The neuron activates on the discourse marker “apparently,” i.e. hedge or qualifier adverbs introducing information as uncertain or hearsay.

    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
    .Hosting
    -0.07
     شاخه
    -0.07
     OD
    -0.07
     VI
    -0.06
    =value
    -0.06
     hlavní
    -0.06
     شخصیت
    -0.06
    	V
    -0.06
    _terms
    -0.06
    之
    -0.06
    POSITIVE LOGITS
     apparently
    0.11
     Apparently
    0.10
    Apparently
    0.09
     apparent
    0.07
     unclear
    0.07
     Beat
    0.07
    mey
    0.06
     essentially
    0.06
     ostensibly
    0.06
     coal
    0.06
    Activations Density 0.010%

    No Known Activations