© 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. 105216
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and conjunctions indicating uncertainty or complexity of situations

    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
     Norris
    -0.07
    hani
    -0.07
    aron
    -0.06
    pd
    -0.06
    2
    -0.06
    erson
    -0.06
    tingham
    -0.06
    3
    -0.06
    thus
    -0.06
    lobal
    -0.06
    POSITIVE LOGITS
     maybe
    0.08
     perhaps
    0.07
     because
    0.07
     Hindered
    0.07
     dieta
    0.07
     Orth
    0.07
    Orth
    0.07
    سÙĪ
    0.06
    дÑĢеÑģ
    0.06
    ãĤ¦ãĤ£
    0.06
    Activations Density 0.004%

    No Known Activations