© 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. 86062
    Prev
    Next
    INDEX
    Explanations

    timestamps or time-related information

    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
    itters
    -0.07
    ecess
    -0.07
    iland
    -0.07
    isme
    -0.06
    isma
    -0.06
    klä
    -0.06
    RTL
    -0.06
     civ
    -0.06
    stead
    -0.06
    JB
    -0.06
    POSITIVE LOGITS
    SourceType
    0.06
    erse
    0.06
    ucus
    0.06
    ersions
    0.06
    PubMed
    0.06
    LATED
    0.06
    nage
    0.06
    mers
    0.06
    ource
    0.06
    RICS
    0.05
    Activations Density 0.000%

    No Known Activations