© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 93776
    Prev
    Next
    INDEX
    Explanations

    terms related to transparency and honesty in pricing or fees

    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
    _GENERIC
    -0.06
    OTOR
    -0.06
    ãĥ¼ãĥij
    -0.05
    ectl
    -0.05
     cr
    -0.05
    uide
    -0.05
    zeug
    -0.05
     trá»įng
    -0.05
    ditor
    -0.05
     /*!↵
    -0.05
    POSITIVE LOGITS
     hidden
    0.12
    hidden
    0.10
    -hidden
    0.10
     extras
    0.09
     ÑģкÑĢÑĭ
    0.08
     charges
    0.08
     concealed
    0.08
     surprises
    0.08
    Hidden
    0.08
     Hidden
    0.08
    Activations Density 0.006%

    No Known Activations