© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 107367
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to methods and systems for data processing and communication

    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
     crit
    -0.06
    ahi
    -0.06
     cup
    -0.06
     qualifying
    -0.06
    boxed
    -0.06
     Ensemble
    -0.06
     clearColor
    -0.06
    umi
    -0.06
    IFT
    -0.05
    umo
    -0.05
    POSITIVE LOGITS
    chor
    0.07
    /resource
    0.07
    legen
    0.07
    Peer
    0.07
    chnitt
    0.06
    .flink
    0.06
    igua
    0.06
    ufen
    0.06
    çłĶç©¶æīĢ
    0.06
    xae
    0.06
    Activations Density 0.004%

    No Known Activations