© 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. 2238
    Prev
    Next
    INDEX
    Explanations

    ellipses or pauses in text that suggest a dramatic or ongoing thought

    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
    _PG
    -0.07
    ries
    -0.07
    ulf
    -0.07
    /or
    -0.07
    ulo
    -0.07
    é¼ĵ
    -0.07
     [=
    -0.07
    è©
    -0.06
    'gc
    -0.06
    hide
    -0.06
    POSITIVE LOGITS
    MMdd
    0.06
    licting
    0.06
    åľ°
    0.06
    anmar
    0.06
    opian
    0.06
    æľµ
    0.06
    اشÛĮ
    0.06
    IFO
    0.06
    sdale
    0.06
    663
    0.06
    Activations Density 0.017%

    No Known Activations