© 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. 87944
    Prev
    Next
    INDEX
    Explanations

    timestamps and measurements related to observations in research studies

    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
     ฿
    -0.08
    å¾ĭ
    -0.08
    ker
    -0.07
    yne
    -0.07
    jah
    -0.07
    ktor
    -0.07
    /respond
    -0.07
     tomorrow
    -0.07
     tonight
    -0.07
    """č↵
    -0.07
    POSITIVE LOGITS
    ornings
    0.07
    intColor
    0.06
     visits
    0.06
    onian
    0.06
    tern
    0.06
     visited
    0.06
     spent
    0.06
     visit
    0.06
     Opport
    0.06
    ripe
    0.06
    Activations Density 0.025%

    No Known Activations