© 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. 15-LLAMASCOPE-RES-131K
    11. 62118
    Prev
    Next
    INDEX
    Explanations

    the preposition "to."

    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
     rein
    -0.07
    act
    -0.07
     Hutchinson
    -0.06
    ument
    -0.06
     Åŀu
    -0.06
    RT
    -0.06
     Bilim
    -0.05
    TO
    -0.05
     util
    -0.05
    eps
    -0.05
    POSITIVE LOGITS
    _Lean
    0.08
    isko
    0.08
    ìĬ¹
    0.08
    .scalablytyped
    0.07
    chner
    0.07
    gba
    0.07
    _Tis
    0.07
    vais
    0.07
    .UnitTesting
    0.07
    .MixedReality
    0.07
    Activations Density 0.013%

    No Known Activations