© 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. 29456
    Prev
    Next
    INDEX
    Explanations

    keywords related to programming or software structure

    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
    Ø®ÙĪ
    -0.07
    ione
    -0.06
    zo
    -0.06
    agan
    -0.06
    ile
    -0.06
    аÑģÑĤи
    -0.06
    li
    -0.06
    idi
    -0.06
    ni
    -0.06
    ra
    -0.06
    POSITIVE LOGITS
    alon
    0.09
    oenix
    0.07
    eza
    0.07
    sob
    0.07
    Äįin
    0.07
    mente
    0.07
    cido
    0.07
    s
    0.07
    upert
    0.06
    ipur
    0.06
    Activations Density 0.001%

    No Known Activations