© 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. 5-LLAMASCOPE-RES-131K
    11. 125796
    Prev
    Next
    INDEX
    Explanations

    terms related to navigation and document organization

    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
    ++
    -0.06
    era
    -0.06
    anel
    -0.06
    icos
    -0.06
    ruba
    -0.06
    eÄį
    -0.06
    egas
    -0.06
    alat
    -0.06
    uges
    -0.06
    processable
    -0.06
    POSITIVE LOGITS
    isku
    0.08
     -*-č↵
    0.08
    sted
    0.06
    289
    0.06
    ifes
    0.06
    à¸Ĺร
    0.06
    cke
    0.06
    wayne
    0.06
    WAYS
    0.06
    chter
    0.06
    Activations Density 0.000%

    No Known Activations