© 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. 15-LLAMASCOPE-RES-131K
    11. 87886
    Prev
    Next
    INDEX
    Explanations

    references to specific time periods, particularly those related to the mid-20th century

    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
    ome
    -0.07
    ewis
    -0.06
    buz
    -0.06
    egg
    -0.06
    ấn
    -0.06
    ustin
    -0.06
     both
    -0.06
     Toll
    -0.06
     Lewis
    -0.05
     Tribe
    -0.05
    POSITIVE LOGITS
    summer
    0.07
     Kız
    0.07
     å¤
    0.07
    ritel
    0.07
    range
    0.07
    ately
    0.07
    variant
    0.07
    galement
    0.07
    rible
    0.06
    Ĥæķ°
    0.06
    Activations Density 0.008%

    No Known Activations