© 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. 78603
    Prev
    Next
    INDEX
    Explanations

    the preposition "of" in various 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
    imar
    -0.07
    irst
    -0.07
    urus
    -0.07
    ucer
    -0.07
    etur
    -0.07
    iry
    -0.07
    ",__
    -0.07
    adir
    -0.06
    roids
    -0.06
    lÃŃ
    -0.06
    POSITIVE LOGITS
     us
    0.08
     those
    0.06
     readers
    0.06
     Dove
    0.06
    odge
    0.06
    ï
    0.06
     concern
    0.06
     whom
    0.06
    oth
    0.06
    ê°Ļ
    0.05
    Activations Density 0.003%

    No Known Activations