© 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. 103691
    Prev
    Next
    INDEX
    Explanations

    expressions of ownership or possession

    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
    znik
    -0.07
    émon
    -0.07
    опиÑģ
    -0.07
    weis
    -0.07
    ivan
    -0.07
    _allocator
    -0.06
    idor
    -0.06
    ä¸į足
    -0.06
    ãĥ¶
    -0.06
    åĬ
    -0.06
    POSITIVE LOGITS
     already
    0.08
    already
    0.08
    pra
    0.07
    .LayoutStyle
    0.07
     sup
    0.07
    nave
    0.07
     Heller
    0.07
    uem
    0.06
    _FULLSCREEN
    0.06
    اØŃØ©
    0.06
    Activations Density 0.029%

    No Known Activations