© 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. 72009
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate transitions or anticipation in the narrative

    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
    ABCDEFGHI
    -0.07
    ipop
    -0.07
    _inactive
    -0.07
    rotch
    -0.07
    orraine
    -0.06
    éī
    -0.06
    straints
    -0.06
    buffers
    -0.06
    ENCHMARK
    -0.06
    ewis
    -0.06
    POSITIVE LOGITS
     meanwhile
    0.17
     meantime
    0.15
     Meanwhile
    0.15
    Meanwhile
    0.14
     currently
    0.10
    currently
    0.10
     Until
    0.10
     Till
    0.10
     presently
    0.10
     interim
    0.09
    Activations Density 0.084%

    No Known Activations