© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 118617
    Prev
    Next
    INDEX
    Explanations

    phrases and concepts related to gambling and lottery games

    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
    avana
    -0.07
    errat
    -0.07
    vard
    -0.06
    :frame
    -0.06
    ulur
    -0.06
    isoft
    -0.06
     Defensive
    -0.06
    icerca
    -0.06
    ulu
    -0.06
    avan
    -0.06
    POSITIVE LOGITS
     landing
    0.08
     landed
    0.08
     combinations
    0.07
    ustil
    0.07
     outcome
    0.07
     Landing
    0.07
    outcome
    0.06
     lands
    0.06
    ög
    0.06
     answer
    0.06
    Activations Density 0.006%

    No Known Activations