© 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. 107481
    Prev
    Next
    INDEX
    Explanations

    references to external links or resources

    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
    oty
    -0.07
    lider
    -0.07
    _NS
    -0.07
    ikler
    -0.07
    .initState
    -0.06
     orderby
    -0.06
    èo
    -0.06
     AQ
    -0.06
    avaÅŁ
    -0.06
    รà¸Ķ
    -0.06
    POSITIVE LOGITS
     external
    0.15
    external
    0.14
    External
    0.13
     External
    0.12
    opens
    0.12
    _external
    0.11
     extern
    0.10
    å¤ĸ
    0.10
    Opens
    0.10
     opens
    0.09
    Activations Density 0.031%

    No Known Activations