© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 90077
    Prev
    Next
    INDEX
    Explanations

    references to less-traveled or off-the-beaten-path locations

    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
    gest
    -0.07
     subsidi
    -0.06
    ottle
    -0.06
    ç¸
    -0.06
     vra
    -0.06
     Gest
    -0.06
    usz
    -0.06
     Verfüg
    -0.06
    adies
    -0.06
    gart
    -0.05
    POSITIVE LOGITS
    oso
    0.07
    >Main
    0.07
    StateManager
    0.07
    zcze
    0.07
    GGLE
    0.07
    üstü
    0.06
    <main
    0.06
    extr
    0.06
    ButtonModule
    0.06
    .iOS
    0.06
    Activations Density 0.001%

    No Known Activations