© 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. 9-LLAMASCOPE-RES-131K
    11. 97628
    Prev
    Next
    INDEX
    Explanations

    references to educational or informational resources

    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
    Multiplicity
    -0.08
    enza
    -0.07
    irie
    -0.07
    MAND
    -0.07
    mada
    -0.07
    ãĥ³ãĥĨãĤ£
    -0.07
    TestCategory
    -0.07
    trx
    -0.07
    amer
    -0.07
    erk
    -0.07
    POSITIVE LOGITS
     indu
    0.06
    iod
    0.06
    ALES
    0.06
     Bing
    0.05
     Nancy
    0.05
     Pere
    0.05
     cul
    0.05
     Clarke
    0.05
    Ĵ
    0.05
     corrupt
    0.05
    Activations Density 0.017%

    No Known Activations