© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 27236
    Prev
    Next
    INDEX
    Explanations

    concepts and terms related to economic transactions and property ownership

    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
     Stocks
    -0.06
    nev
    -0.06
    nze
    -0.06
     Klein
    -0.06
    pit
    -0.06
     Sever
    -0.06
     downfall
    -0.06
    æī±
    -0.06
    OND
    -0.06
    eria
    -0.05
    POSITIVE LOGITS
    adians
    0.07
    edii
    0.07
    ovice
    0.07
    ovah
    0.07
    exus
    0.07
    itoris
    0.07
    unma
    0.07
    ìĦŃ
    0.07
    containers
    0.06
    ACHI
    0.06
    Activations Density 0.008%

    No Known Activations