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

    Neuronpedia

    Jacobian LensNEW
    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. 17-LLAMASCOPE-RES-131K
    11. 130714
    Prev
    Next
    INDEX
    Explanations

    points of view or statements reflecting personal opinions

    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
    oku
    -0.07
    coma
    -0.07
    insula
    -0.07
    wers
    -0.06
    ataka
    -0.06
    ModelError
    -0.06
    OfDay
    -0.06
    ENS
    -0.06
    Bracket
    -0.06
    оÑī
    -0.06
    POSITIVE LOGITS
     earlier
    0.11
     during
    0.10
     recently
    0.10
     twice
    0.09
     recent
    0.09
     when
    0.08
     During
    0.08
     Earlier
    0.08
    æĽ¾
    0.08
     durante
    0.08
    Activations Density 0.032%

    No Known Activations