© 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. 93984
    Prev
    Next
    INDEX
    Explanations

    information related to winning amounts and payout structures in gambling contexts

    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
    punk
    -0.07
    ambi
    -0.07
    77
    -0.06
    936
    -0.06
    776
    -0.06
     komb
    -0.06
     Sheldon
    -0.06
     redundant
    -0.06
    ena
    -0.06
    EMBER
    -0.06
    POSITIVE LOGITS
    imas
    0.07
    ádu
    0.07
    imap
    0.07
     nues
    0.07
    zcze
    0.06
    abor
    0.06
     Grimm
    0.06
    atoria
    0.06
    Clazz
    0.06
     Britt
    0.06
    Activations Density 0.007%

    No Known Activations