© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 6504
    Prev
    Next
    INDEX
    Explanations

    biblical passages

    np_max-act · gemini-2.0-flash

    This neuron detects the character sequence “us” (e.g. in words like “Emmaus” or the standalone token “us”).

    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
     clutch
    -0.07
    세요
    -0.07
    Boy
    -0.06
    meteor
    -0.06
    OWN
    -0.06
    	layout
    -0.06
     woo
    -0.06
    арів
    -0.06
     cattle
    -0.06
     culp
    -0.06
    POSITIVE LOGITS
    riendly
    0.07
    -alpha
    0.07
    >tagger
    0.06
    Lbl
    0.06
     liberal
    0.06
    (logging
    0.06
    ection
    0.06
    imestone
    0.06
     exposes
    0.06
     граф
    0.06
    Activations Density 0.005%

    No Known Activations