© 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. 17-LLAMASCOPE-RES-131K
    11. 72613
    Prev
    Next
    INDEX
    Explanations

    terminology related to business achievements and success metrics

    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
    afc
    -0.07
    utsche
    -0.07
     ô
    -0.06
     Kre
    -0.06
    cej
    -0.06
    pls
    -0.06
    vlc
    -0.06
    ologia
    -0.06
    ænd
    -0.06
     compos
    -0.06
    POSITIVE LOGITS
    iltr
    0.07
     upcoming
    0.07
    tiv
    0.06
     Invocation
    0.06
    inos
    0.06
    rowth
    0.06
    rd
    0.06
     deleg
    0.06
    vas
    0.06
    lei
    0.06
    Activations Density 0.001%

    No Known Activations