© 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. 119611
    Prev
    Next
    INDEX
    Explanations

    references to legal terms and conditions

    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
    VERTISEMENT
    -0.07
    estr
    -0.07
    achuset
    -0.07
    ÃŃg
    -0.07
    ıa
    -0.07
     bana
    -0.07
    ستÙĩ
    -0.06
     ci
    -0.06
    enton
    -0.06
    лев
    -0.06
    POSITIVE LOGITS
    mpz
    0.06
    acha
    0.06
     IC
    0.06
    by
    0.06
    stin
    0.06
    opis
    0.06
    mps
    0.06
    Ms
    0.05
    ниÑĩ
    0.05
    aight
    0.05
    Activations Density 0.000%

    No Known Activations