© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 74402
    Prev
    Next
    INDEX
    Explanations

    conditional phrases suggesting possibilities or recommendations

    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
    essler
    -0.07
    tainment
    -0.07
    CAA
    -0.07
    caa
    -0.06
     DeÄŁ
    -0.06
    udeau
    -0.06
    ohl
    -0.06
    ioni
    -0.06
     Dear
    -0.06
    dia
    -0.06
    POSITIVE LOGITS
    notated
    0.07
     Lopez
    0.07
    olis
    0.07
    ulent
    0.06
     best
    0.06
     preferred
    0.06
    ekim
    0.06
     López
    0.06
    _decorator
    0.06
     options
    0.06
    Activations Density 0.023%

    No Known Activations