© 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. 42395
    Prev
    Next
    INDEX
    Explanations

    instances of publication dates and associated publishing statuses

    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
    มห
    -0.06
     Microsystems
    -0.06
    169
    -0.06
    phy
    -0.06
    åĬ
    -0.06
    iron
    -0.06
    alam
    -0.06
    546
    -0.06
    423
    -0.06
     whom
    -0.06
    POSITIVE LOGITS
    rias
    0.08
    icensed
    0.07
    orado
    0.07
    pard
    0.07
    ouz
    0.07
    olina
    0.06
    autor
    0.06
    hled
    0.06
    Ngh
    0.06
    ivor
    0.06
    Activations Density 0.004%

    No Known Activations