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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 129044
    Prev
    Next
    INDEX
    Explanations

    quoted dialogue or statements within the 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
     nÃło
    -0.09
    eft
    -0.08
     ...(
    -0.08
    eron
    -0.08
    ¦¬
    -0.08
    @nate
    -0.07
    ses
    -0.07
    Ưá»
    -0.07
    .GroupLayout
    -0.07
    ácil
    -0.07
    POSITIVE LOGITS
    ward
    0.08
    页éĿ¢åŃĺæ¡£å¤ĩ份
    0.08
    egral
    0.07
    bsite
    0.07
    orary
    0.07
     latter
    0.07
    ly
    0.07
    n
    0.07
    theless
    0.07
    ir
    0.07
    Activations Density 0.037%

    No Known Activations