© 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. 74291
    Prev
    Next
    INDEX
    Explanations

    calls to action related to registration or signing up

    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
     Paras
    -0.07
    idis
    -0.07
    Ñıг
    -0.07
    oli
    -0.06
    hest
    -0.06
    dale
    -0.06
    ese
    -0.06
    co
    -0.06
    idelity
    -0.06
    ric
    -0.05
    POSITIVE LOGITS
    há
    0.07
    expo
    0.07
    .synthetic
    0.07
    ounters
    0.07
    ÎŃα
    0.07
    zug
    0.07
    ündeki
    0.07
    udent
    0.07
    .Îł
    0.07
     Quảng
    0.07
    Activations Density 0.001%

    No Known Activations