© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 70773
    Prev
    Next
    INDEX
    Explanations

    timestamps and time indications within text

    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
    868
    -0.06
    eson
    -0.06
    200
    -0.06
    419
    -0.06
    935
    -0.06
    åħĪ
    -0.06
    591
    -0.06
    472
    -0.05
    (
    -0.05
    787
    -0.05
    POSITIVE LOGITS
     crossorigin
    0.08
    SetBranch
    0.08
     addCriterion
    0.08
     RuntimeObject
    0.08
    chedulers
    0.08
    owitz
    0.08
     Pazar
    0.08
    EmptyEntries
    0.08
    GuidId
    0.08
    IColor
    0.07
    Activations Density 0.002%

    No Known Activations