© 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 EvalsExportsAPI 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. 78607
    Prev
    Next
    INDEX
    Explanations

    concepts related to directional context or physical locations

    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
    ç£
    -0.09
    ãĥŃãĥ³
    -0.07
    avra
    -0.07
    _PICTURE
    -0.07
    ë¡
    -0.07
    leck
    -0.07
    ares
    -0.07
    earn
    -0.06
    ccione
    -0.06
    amac
    -0.06
    POSITIVE LOGITS
     that
    0.07
    tober
    0.07
     where
    0.07
    taire
    0.06
    stile
    0.06
    annel
    0.06
    üm
    0.06
     known
    0.06
    mscorlib
    0.06
     multiple
    0.05
    Activations Density 0.025%

    No Known Activations