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

    Neuronpedia

    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. 17-LLAMASCOPE-RES-131K
    11. 60425
    Prev
    Next
    INDEX
    Explanations

    words related to climbing or mountains

    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
    ivant
    -0.08
    ILLE
    -0.07
    ille
    -0.07
    iros
    -0.07
    fluid
    -0.07
    offs
    -0.07
    788
    -0.06
    sein
    -0.06
     clue
    -0.06
    alia
    -0.06
    POSITIVE LOGITS
    çªģ
    0.07
     Grape
    0.07
    YPE
    0.07
    -ÑĤо
    0.07
     jist
    0.07
    abeth
    0.06
    actic
    0.06
    IDGET
    0.06
    AZY
    0.06
    adr
    0.06
    Activations Density 0.003%

    No Known Activations