© 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. 17-LLAMASCOPE-RES-131K
    11. 85372
    Prev
    Next
    INDEX
    Explanations

    numerical data and parameters related to scientific measurements

    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
     prim
    -0.06
     Harden
    -0.06
    ken
    -0.06
    ìĹ´
    -0.06
     Schwarz
    -0.06
    -turned
    -0.06
    laden
    -0.06
     Ñĥвид
    -0.06
    PRINTF
    -0.06
    eden
    -0.06
    POSITIVE LOGITS
    ruc
    0.07
     etc
    0.07
    éru
    0.07
    adiens
    0.06
    FragmentManager
    0.06
     Arabia
    0.06
    abbo
    0.06
    ahtar
    0.06
    atz
    0.06
    ằm
    0.06
    Activations Density 0.024%

    No Known Activations