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

    Neuronpedia

    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. 86760
    Prev
    Next
    INDEX
    Explanations

    references to lines of code or formatted instructions

    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
    lev
    -0.07
    wing
    -0.07
    ilio
    -0.06
    ÙĪاÙĨ
    -0.06
    TAIL
    -0.06
    alim
    -0.06
    olland
    -0.06
    anz
    -0.06
    indexed
    -0.06
    wil
    -0.06
    POSITIVE LOGITS
     noqa
    0.07
    ipse
    0.06
    egie
    0.06
    ÑĢоÑģÑĤо
    0.06
    DBObject
    0.06
    istrovstvÃŃ
    0.06
    eve
    0.06
    ivas
    0.06
    ometr
    0.06
     pard
    0.06
    Activations Density 0.000%

    No Known Activations