© 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. 88199
    Prev
    Next
    INDEX
    Explanations

    words related to match results or competitive outcomes

    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
    bows
    -0.07
    ัà¸ķ
    -0.06
    orman
    -0.06
    uzz
    -0.06
    代
    -0.06
    ties
    -0.06
    opus
    -0.06
    alars
    -0.06
    usi
    -0.06
    ode
    -0.06
    POSITIVE LOGITS
    (es
    0.09
     match
    0.09
     Match
    0.08
    -match
    0.08
    (match
    0.07
    .match
    0.07
    match
    0.07
    .Match
    0.07
    esa
    0.07
     MATCH
    0.07
    Activations Density 0.007%

    No Known Activations