© 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. 60942
    Prev
    Next
    INDEX
    Explanations

    references to ongoing series or collections of articles

    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
    -0.06
    akk
    -0.06
    inae
    -0.06
     facilities
    -0.05
     General
    -0.05
     te
    -0.05
     Han
    -0.05
    ép
    -0.05
     Tier
    -0.05
    723
    -0.05
    POSITIVE LOGITS
    ç³»åĪĹ
    0.10
    ãĤ·ãĥªãĥ¼ãĤº
    0.10
    weekly
    0.09
     series
    0.09
    feature
    0.09
    azio
    0.09
     feature
    0.09
     columna
    0.08
    .series
    0.08
    Ø´ÙĨ
    0.08
    Activations Density 0.016%

    No Known Activations