© 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. 95073
    Prev
    Next
    INDEX
    Explanations

    details related to historical events, particularly battles and military statistics

    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
    ImageContext
    -0.08
     Antar
    -0.07
    BackingField
    -0.07
    ulton
    -0.07
    .DEFINE
    -0.06
    raki
    -0.06
    _Osc
    -0.06
     Bey
    -0.06
    üst
    -0.06
     lez
    -0.06
    POSITIVE LOGITS
     Sheffield
    0.07
    VC
    0.07
     prime
    0.07
     Vietnam
    0.06
    Bounding
    0.06
    òn
    0.06
    chk
    0.06
    ongs
    0.06
    _perf
    0.06
    Op
    0.06
    Activations Density 0.004%

    No Known Activations