© 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. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 97512
    Prev
    Next
    INDEX
    Explanations

    references to SMS and messaging services

    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
    bst
    -0.06
    æł
    -0.06
    iber
    -0.06
     Christ
    -0.06
    riv
    -0.06
    (Parser
    -0.06
     ot
    -0.05
    andest
    -0.05
    ibold
    -0.05
     fl
    -0.05
    POSITIVE LOGITS
    èĥŀ
    0.07
    staking
    0.07
    hiro
    0.07
    ettes
    0.07
    vailable
    0.07
    .obtain
    0.07
    orca
    0.07
    ëĦ·
    0.07
    elik
    0.07
    lepÅ¡ÃŃ
    0.07
    Activations Density 0.004%

    No Known Activations