© 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. 39835
    Prev
    Next
    INDEX
    Explanations

    details regarding packaging and transport procedures

    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
    pz
    -0.07
    ãģ¸ãģ¨
    -0.07
     culmination
    -0.07
    redo
    -0.07
    梨
    -0.06
    ENTIC
    -0.06
    OOT
    -0.06
    pretty
    -0.06
    его
    -0.06
     our
    -0.06
    POSITIVE LOGITS
     preferably
    0.08
    oji
    0.07
    esk
    0.07
    ieber
    0.07
    aÄį
    0.06
     Femme
    0.06
    -/
    0.06
    aket
    0.06
    imas
    0.06
    agna
    0.06
    Activations Density 0.003%

    No Known Activations