© 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. 123696
    Prev
    Next
    INDEX
    Explanations

    spatial or directional terms referring to position and movement

    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
    znik
    -0.07
    reib
    -0.07
    .scalablytyped
    -0.07
    ivre
    -0.06
    619
    -0.06
    akter
    -0.06
    idental
    -0.06
    hta
    -0.06
    acker
    -0.06
    adan
    -0.06
    POSITIVE LOGITS
    ModelProperty
    0.07
    ê°IJ
    0.07
     Arte
    0.07
     Tradable
    0.06
    elsey
    0.06
    ÃĹ↵↵
    0.06
    .Payload
    0.06
     Away
    0.06
     Artifact
    0.06
     ãĤŃãĥ£
    0.06
    Activations Density 0.039%

    No Known Activations