© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 70632
    Prev
    Next
    INDEX
    Explanations

    references to specific topics and discussions in forums

    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
    aniel
    -0.07
    atar
    -0.07
    linger
    -0.06
    pa
    -0.06
     ÄĮesk
    -0.06
    нка
    -0.06
    rieve
    -0.05
    osis
    -0.05
    živ
    -0.05
    awei
    -0.05
    POSITIVE LOGITS
    ENTA
    0.08
    -toggler
    0.07
    ouri
    0.07
    ousand
    0.07
    agem
    0.06
    šov
    0.06
    ainted
    0.06
    CISION
    0.06
    entieth
    0.06
     migrationBuilder
    0.06
    Activations Density 0.001%

    No Known Activations