© 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. 94998
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate instructions or guidance

    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
    Äįel
    -0.07
    ži
    -0.07
    ickey
    -0.06
     viewers
    -0.06
    osit
    -0.06
    aylor
    -0.06
    isé
    -0.06
    imap
    -0.06
     áº
    -0.06
    abyrin
    -0.06
    POSITIVE LOGITS
     signs
    0.11
    vidence
    0.09
     Signs
    0.08
     opportunities
    0.08
     opportunity
    0.07
     Opportunities
    0.07
     evidence
    0.07
    753
    0.07
     Opportunity
    0.07
    ways
    0.07
    Activations Density 0.009%

    No Known Activations