© 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. 73662
    Prev
    Next
    INDEX
    Explanations

    instances of phrases indicating location or positioning

    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
    ãĥ¼ãĥ©
    -0.08
    steller
    -0.08
    chet
    -0.08
    hunt
    -0.08
    eros
    -0.07
    .INSTANCE
    -0.07
    izes
    -0.07
    lettes
    -0.07
    lette
    -0.07
    hin
    -0.07
    POSITIVE LOGITS
     how
    0.08
     least
    0.07
     whether
    0.06
     differently
    0.06
     ways
    0.06
    umba
    0.06
    ypical
    0.06
     partir
    0.06
    compass
    0.06
     hoe
    0.06
    Activations Density 0.017%

    No Known Activations