© 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. 118906
    Prev
    Next
    INDEX
    Explanations

    phrases related to baseline measurements and their assessments in various contexts

    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
    RICS
    -0.06
    fan
    -0.06
     unofficial
    -0.06
    ocale
    -0.06
     GIT
    -0.06
    ildi
    -0.06
    íĥĦ
    -0.05
    GIT
    -0.05
    /Images
    -0.05
     Tat
    -0.05
    POSITIVE LOGITS
     baseline
    0.11
    baseline
    0.10
    /default
    0.10
    /original
    0.09
    /native
    0.08
    /base
    0.08
    Baseline
    0.08
    iative
    0.07
    _baseline
    0.07
     iken
    0.07
    Activations Density 0.112%

    No Known Activations