© 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. 29055
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases indicating location or position

    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
    eh
    -0.07
    chn
    -0.07
    pit
    -0.06
     Lean
    -0.06
    oran
    -0.06
    ly
    -0.06
    achat
    -0.06
    lyph
    -0.06
    arn
    -0.06
    lea
    -0.06
    POSITIVE LOGITS
     bottom
    0.07
    MethodImpl
    0.07
    foy
    0.07
    439
    0.07
    askell
    0.06
    oyal
    0.06
    _ONCE
    0.06
    -parse
    0.06
    -bottom
    0.06
    omentum
    0.06
    Activations Density 0.010%

    No Known Activations