© 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. 91947
    Prev
    Next
    INDEX
    Explanations

    phrases indicating something that has previously occurred or been mentioned

    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
     lagi
    -0.09
    ijn
    -0.08
    æĥij
    -0.07
    asha
    -0.07
     Again
    -0.07
    again
    -0.07
    nodoc
    -0.07
     again
    -0.07
    ancy
    -0.06
    reek
    -0.06
    POSITIVE LOGITS
     once
    0.07
     Qed
    0.06
    once
    0.06
    quel
    0.06
    evin
    0.06
    ordinal
    0.06
     twice
    0.06
    ãĥŃãĥ³
    0.06
    ãģĭ
    0.06
    lesen
    0.05
    Activations Density 0.013%

    No Known Activations