© 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. 15-LLAMASCOPE-RES-131K
    11. 1424
    Prev
    Next
    INDEX
    Explanations

    keywords related to data management and processing techniques

    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
    odzi
    -0.07
    ogi
    -0.07
    _lineno
    -0.07
    VML
    -0.06
    ẩm
    -0.06
    rades
    -0.06
    ält
    -0.06
    orta
    -0.06
     jackpot
    -0.06
    cao
    -0.06
    POSITIVE LOGITS
     techniques
    0.07
     technique
    0.07
    instead
    0.07
     вмеÑģÑĤ
    0.07
    alous
    0.07
     instead
    0.07
    åĬĽãĤĴ
    0.06
     tactics
    0.06
    adesh
    0.06
    dum
    0.06
    Activations Density 0.109%

    No Known Activations