© 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. 55610
    Prev
    Next
    INDEX
    Explanations

    references to numerical identifiers or codes associated with specific items or data

    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
    ish
    -0.12
       
    -0.09
    led
    -0.09
    Ø©
    -0.09
    ey
    -0.09
    fox
    -0.08
    liness
    -0.07
    nd
    -0.07
     latter
    -0.07
    ald
    -0.07
    POSITIVE LOGITS
    ëĭ¤
    0.10
    ively
    0.10
    ว
    0.09
    çĦ¶
    0.09
    gle
    0.09
    acing
    0.08
    andalone
    0.08
    nova
    0.08
    .nz
    0.08
    θα
    0.08
    Activations Density 0.119%

    No Known Activations