© 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. 55941
    Prev
    Next
    INDEX
    Explanations

    instances of the word "into" and its related phrases

    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
    inoa
    -0.08
    ted
    -0.07
    idor
    -0.07
    al
    -0.07
    inous
    -0.07
    ed
    -0.06
     bench
    -0.06
    INO
    -0.06
    aga
    -0.06
    uÃŃ
    -0.06
    POSITIVE LOGITS
    quate
    0.06
    oves
    0.06
    embr
    0.06
     Pit
    0.06
     action
    0.06
    аки
    0.06
    razione
    0.06
    ANI
    0.06
     milion
    0.06
    段
    0.06
    Activations Density 0.026%

    No Known Activations