© 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. 60899
    Prev
    Next
    INDEX
    Explanations

    phrases indicative of anticipated events or outcomes

    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
     various
    -0.06
     Sant
    -0.05
    etine
    -0.05
     Alley
    -0.05
     one
    -0.05
     trop
    -0.05
     pol
    -0.05
    еÑĤе
    -0.05
     Various
    -0.05
    etically
    -0.05
    POSITIVE LOGITS
     else
    0.11
    else
    0.10
     happens
    0.08
     ELSE
    0.08
     happened
    0.08
    _else
    0.08
    룬
    0.07
    yang
    0.07
     happening
    0.07
    ilden
    0.07
    Activations Density 0.033%

    No Known Activations