© 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. 77100
    Prev
    Next
    INDEX
    Explanations

    references to timelines and scheduling 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
    orum
    -0.07
     unto
    -0.07
    919
    -0.06
    lok
    -0.06
    862
    -0.06
    ÑĢаж
    -0.06
    689
    -0.06
    overe
    -0.06
    alam
    -0.05
     convict
    -0.05
    POSITIVE LOGITS
     release
    0.08
     releases
    0.07
    release
    0.07
    -release
    0.07
    ÑĤÑı
    0.07
    oka
    0.06
    irk
    0.06
     vyp
    0.06
     Releases
    0.06
     delivery
    0.06
    Activations Density 0.022%

    No Known Activations