© 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. 128707
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives related to size and duration

    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
     Organ
    -0.06
    ebra
    -0.06
    виÑĩай
    -0.06
    .microsoft
    -0.06
    azer
    -0.06
     dop
    -0.06
     god
    -0.06
    aso
    -0.05
    ("[%
    -0.05
    ead
    -0.05
    POSITIVE LOGITS
     compared
    0.10
    arella
    0.09
     affair
    0.09
    -Sah
    0.08
    ĵåIJį
    0.07
    relative
    0.07
     affairs
    0.07
    RelativeTo
    0.07
     Relative
    0.07
    ervas
    0.07
    Activations Density 0.036%

    No Known Activations