© 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. 61077
    Prev
    Next
    INDEX
    Explanations

    references to collaboration and assistance in achieving goals

    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
    aisy
    -0.07
    ãĥ¼ãĤ¹ãĥĪ
    -0.06
    holm
    -0.06
    .Requires
    -0.06
    adows
    -0.06
    æ®
    -0.06
     ong
    -0.06
    acock
    -0.06
    VILLE
    -0.06
    ews
    -0.06
    POSITIVE LOGITS
     soon
    0.07
     hopefully
    0.07
     we
    0.07
    ogg
    0.07
     Easily
    0.07
     together
    0.06
     can
    0.06
     magic
    0.06
    izo
    0.06
     поÑģÑĤеп
    0.06
    Activations Density 0.016%

    No Known Activations