© 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. 107444
    Prev
    Next
    INDEX
    Explanations

    expressions of agreement or affirmation

    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
    .BackgroundImageLayout
    -0.06
    ï
    -0.06
    xy
    -0.06
    sie
    -0.06
    oce
    -0.06
     RE
    -0.06
     whats
    -0.05
     Sunder
    -0.05
    ples
    -0.05
    over
    -0.05
    POSITIVE LOGITS
     indeed
    0.07
     ragaz
    0.07
    ObjectName
    0.07
     STDCALL
    0.07
     sir
    0.07
    /left
    0.07
    egasus
    0.07
    JsonValue
    0.07
    Caps
    0.07
    alon
    0.06
    Activations Density 0.007%

    No Known Activations