© 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. 93747
    Prev
    Next
    INDEX
    Explanations

    instances of the word "to" 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
    iento
    -0.08
    arten
    -0.08
    odash
    -0.07
    lish
    -0.07
    ipay
    -0.07
     оз
    -0.07
    akat
    -0.07
    utoff
    -0.07
    kup
    -0.07
    .lp
    -0.07
    POSITIVE LOGITS
    urge
    0.06
     try
    0.06
    ys
    0.06
     emphasis
    0.06
    огод
    0.06
    PIP
    0.06
    sg
    0.06
    ÃŃž
    0.06
     protest
    0.06
     IllegalAccessException
    0.06
    Activations Density 0.031%

    No Known Activations