© 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. 17-LLAMASCOPE-RES-131K
    6. 77557
    Prev
    Next
    INDEX
    Explanations

    terms related to ownership and investment stakes in businesses

    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
    /xhtml
    -0.07
    iaux
    -0.07
    chester
    -0.07
    xing
    -0.07
    ött
    -0.06
    prit
    -0.06
    TODO
    -0.06
    geç
    -0.06
    cole
    -0.06
    uien
    -0.06
    POSITIVE LOGITS
     in
    0.07
    holder
    0.07
     Raven
    0.06
    adro
    0.06
    inker
    0.06
    iller
    0.06
    639
    0.06
    ake
    0.06
    yro
    0.06
    /part
    0.06
    Activations Density 0.004%

    No Known Activations