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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 57736
    Prev
    Next
    INDEX
    Explanations

    empties into body of water

    np_max-act · gemini-2.0-flash

    The neuron activates on terms describing watercourses and their flow (e.g. watershed, catchment, empties, discharges).

    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
    .loc
    -0.07
    	Buffer
    -0.07
     حج
    -0.06
    _MASK
    -0.06
    Ted
    -0.06
     Dir
    -0.06
    Proposal
    -0.06
    ANS
    -0.06
    .say
    -0.06
    markup
    -0.06
    POSITIVE LOGITS
    .dtype
    0.06
    /settings
    0.06
     プロ
    0.06
     THR
    0.06
     army
    0.06
    olucion
    0.06
    RIA
    0.06
    塑
    0.06
    grim
    0.06
    +"<
    0.06
    Activations Density 0.006%

    No Known Activations