© 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. 22-LLAMASCOPE-RES-131K
    11. 3916
    Prev
    Next
    INDEX
    Explanations

    references to historical events and their lessons

    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
    neys
    -0.07
    ukan
    -0.07
    ersen
    -0.07
    pNet
    -0.07
    anted
    -0.07
    YTE
    -0.06
    arness
    -0.06
    .Bot
    -0.06
    ipherals
    -0.06
    zew
    -0.06
    POSITIVE LOGITS
     twentieth
    0.14
     Modern
    0.12
     modern
    0.12
    Modern
    0.11
    195
    0.11
    196
    0.11
     Cold
    0.11
     century
    0.11
    modern
    0.10
    entieth
    0.10
    Activations Density 0.044%

    No Known Activations