© 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. 85339
    Prev
    Next
    INDEX
    Explanations

    questions and expressions of reasoning or justification

    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
    erse
    -0.09
    oret
    -0.09
    ersh
    -0.07
    unks
    -0.06
    eventId
    -0.06
    AXB
    -0.06
     Erg
    -0.06
    ?type
    -0.06
    åıĶ
    -0.06
    _RENDERER
    -0.06
    POSITIVE LOGITS
     titul
    0.07
    eyen
    0.07
    -ending
    0.06
     à¤ĩतन
    0.06
    keh
    0.06
    vig
    0.06
    ç´ļ
    0.06
    (Dialog
    0.06
    uzz
    0.06
     aforementioned
    0.06
    Activations Density 0.053%

    No Known Activations