© 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. 87856
    Prev
    Next
    INDEX
    Explanations

    measurements and comparisons related to data and performance

    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
    anson
    -0.06
     broad
    -0.06
    inker
    -0.06
    ÑıÑģÑĮ
    -0.05
    /cms
    -0.05
    leurs
    -0.05
    ailles
    -0.05
    883
    -0.05
    lest
    -0.05
     semif
    -0.05
    POSITIVE LOGITS
     solely
    0.24
     sole
    0.21
     only
    0.20
     exclusively
    0.20
    -only
    0.19
     ONLY
    0.19
    sole
    0.18
    only
    0.18
     single
    0.17
    _only
    0.17
    Activations Density 0.080%

    No Known Activations