© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 90231
    Prev
    Next
    INDEX
    Explanations

    negative phrases or expressions

    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
    nox
    -0.06
    iosis
    -0.06
    486
    -0.06
    orraine
    -0.06
    hti
    -0.06
    heed
    -0.06
    iev
    -0.06
    ause
    -0.06
    .Reporting
    -0.06
    ISIBLE
    -0.06
    POSITIVE LOGITS
    withstanding
    0.07
     necessarily
    0.07
    lyph
    0.07
    .decorate
    0.07
    icias
    0.07
    akit
    0.06
    _spacing
    0.06
     sure
    0.06
    ellas
    0.06
     affiliated
    0.06
    Activations Density 0.018%

    No Known Activations