Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15-RESID-POST-AA
    6. 24423
    Prev
    Next
    INDEX
    Explanations

    Committee

    np_max-act · gemini-2.0-flash

    The neuron detects named entities—proper nouns like people, organizations, places, dates and other capitalized titles.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RowCount
    -0.08
    	EIF
    -0.08
     however
    -0.07
    ='.$
    -0.07
     how
    -0.07
    textTheme
    -0.07
     시험
    -0.07
    getClientOriginal
    -0.07
    μως
    -0.07
    ABCDEFGHIJKLMNOP
    -0.07
    POSITIVE LOGITS
     cà
    0.06
     favor
    0.06
    &C
    0.06
     pours
    0.06
     gated
    0.06
     perc
    0.06
     слу
    0.06
     memor
    0.06
     marg
    0.06
     solic
    0.06
    Activations Density 22.738%

    No Known Activations