© 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 EvalsExportsinterp-engineNEWAPI 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. 62865
    Prev
    Next
    INDEX
    Explanations

    terms related to skills, capabilities, and career opportunities

    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
    нÑĤ
    -0.06
    ayım
    -0.06
    ooke
    -0.06
    .Entry
    -0.06
     apart
    -0.06
    aras
    -0.06
    iegel
    -0.06
     Apart
    -0.06
    _Entry
    -0.06
    Ïįν
    -0.06
    POSITIVE LOGITS
    tro
    0.07
    buf
    0.06
    ethod
    0.06
    IVAL
    0.06
    asi
    0.06
    ulan
    0.06
    ales
    0.06
    agnost
    0.06
    leur
    0.06
     itemprop
    0.06
    Activations Density 0.006%

    No Known Activations