© 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. 81820
    Prev
    Next
    INDEX
    Explanations

    declarative statements about necessary actions or methods to address various issues

    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
     zwar
    -0.08
    avic
    -0.07
    /helpers
    -0.07
    طاÙĦ
    -0.07
     already
    -0.06
    already
    -0.06
     least
    -0.06
     exactly
    -0.06
     Ere
    -0.06
    stim
    -0.06
    POSITIVE LOGITS
     ever
    0.09
     truly
    0.08
     Truly
    0.07
    æīįèĥ½
    0.07
    amac
    0.07
    sembly
    0.07
     guarantee
    0.07
    羣æŃ£
    0.07
    -ever
    0.07
    oux
    0.07
    Activations Density 0.011%

    No Known Activations