© 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. 106429
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical operations, specifically multiplication

    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
    iw
    -0.08
    872
    -0.08
    obi
    -0.07
    lain
    -0.07
    389
    -0.07
    oca
    -0.07
    ioc
    -0.06
    Äįin
    -0.06
    ward
    -0.06
    kit
    -0.06
    POSITIVE LOGITS
    /div
    0.11
    deaux
    0.09
    plies
    0.08
    .infinity
    0.08
     sclerosis
    0.08
    onu
    0.08
    pliers
    0.08
    plier
    0.07
    inus
    0.07
    PLIC
    0.07
    Activations Density 0.015%

    No Known Activations