© 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. 93174
    Prev
    Next
    INDEX
    Explanations

    instances of the word "present" and its variations, indicating discussions related to presentations and showcases

    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
    ritz
    -0.07
    ñana
    -0.07
     pastoral
    -0.06
    _pes
    -0.06
     GOODMAN
    -0.06
     ÑģÑĤол
    -0.06
     ÙĪظ
    -0.06
    rocessing
    -0.06
    çĴ
    -0.06
    hend
    -0.06
    POSITIVE LOGITS
     ideas
    0.08
    .slides
    0.07
    ooke
    0.06
    _stderr
    0.06
     PowerPoint
    0.06
     plans
    0.06
    ByUrl
    0.06
    edl
    0.06
    lust
    0.06
    cho
    0.06
    Activations Density 0.014%

    No Known Activations