© 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. 106168
    Prev
    Next
    INDEX
    Explanations

    references to rankings or positions within a hierarchy

    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
    nul
    -0.07
     cá
    -0.07
    ucci
    -0.07
    еÑĢк
    -0.07
     Pence
    -0.07
     dear
    -0.06
    eric
    -0.06
    565
    -0.06
     Mits
    -0.06
     näch
    -0.06
    POSITIVE LOGITS
    /top
    0.10
     of
    0.08
    bris
    0.07
    /meta
    0.06
    est
    0.06
    ismo
    0.06
     reaches
    0.06
    pest
    0.06
    azz
    0.06
    .scalablytyped
    0.06
    Activations Density 0.010%

    No Known Activations