© 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. 73274
    Prev
    Next
    INDEX
    Explanations

    phrases expressing the availability of assistance or options for support

    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
     Teknik
    -0.07
    .bundle
    -0.07
    phinx
    -0.07
    Ur
    -0.07
    kaar
    -0.07
    ersh
    -0.07
    urgeon
    -0.07
    iders
    -0.06
    kos
    -0.06
    urr
    -0.06
    POSITIVE LOGITS
     you
    0.08
     rest
    0.07
     YOU
    0.07
     together
    0.06
    unci
    0.06
    AffineTransform
    0.06
     You
    0.06
    519
    0.06
     Tobias
    0.06
    artz
    0.06
    Activations Density 0.011%

    No Known Activations