© 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. 17-LLAMASCOPE-RES-131K
    11. 82624
    Prev
    Next
    INDEX
    Explanations

    mathematical and scientific notation, particularly those related to equations and labels

    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
    eras
    -0.07
    .scalablytyped
    -0.07
    eron
    -0.07
    ão
    -0.07
    :maj
    -0.07
    ìħľ
    -0.06
     поба
    -0.06
    iko
    -0.06
    .ndim
    -0.06
    icity
    -0.06
    POSITIVE LOGITS
    ané
    0.08
    fü
    0.06
    ket
    0.06
     beden
    0.06
    endregion
    0.06
    aley
    0.06
     anywhere
    0.06
    allis
    0.06
    ymm
    0.06
     latter
    0.06
    Activations Density 0.040%

    No Known Activations