© 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. 119226
    Prev
    Next
    INDEX
    Explanations

    references to challenges, contests, and participation activities

    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
     even
    -0.06
     also
    -0.06
     bay
    -0.06
     stream
    -0.06
     might
    -0.06
     sometimes
    -0.06
     Presents
    -0.06
     further
    -0.06
     other
    -0.06
    ovich
    -0.05
    POSITIVE LOGITS
    íĦ¸
    0.09
     خاÙħ
    0.09
    :Register
    0.08
    åıªè¦ģ
    0.08
    Simply
    0.08
    -simple
    0.08
    contri
    0.08
    _entropy
    0.08
     Simply
    0.08
     simplement
    0.07
    Activations Density 0.017%

    No Known Activations