© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 96867
    Prev
    Next
    INDEX
    Explanations

    words related to paddling and canoeing activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bins
    -0.08
    ynes
    -0.07
    AMPL
    -0.07
    INGER
    -0.07
    rors
    -0.07
    alta
    -0.07
    erus
    -0.07
    consts
    -0.07
    osphate
    -0.07
    nown
    -0.07
    POSITIVE LOGITS
    оÑĢÑĤ
    0.06
    illac
    0.06
    åħ¬è·¯
    0.06
    lee
    0.06
    /sw
    0.05
    aved
    0.05
    irket
    0.05
    omin
    0.05
    /router
    0.05
     Burnett
    0.05
    Activations Density 0.002%

    No Known Activations