© 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 EvalsExportsinterp-engineNEWAPI 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. 81042
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a lack of resources or information

    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
    gel
    -0.06
     hopefully
    -0.06
    gers
    -0.05
    ãĥ³ãĥĪ
    -0.05
     should
    -0.05
     certainly
    -0.05
     not
    -0.05
    anging
    -0.05
     whenever
    -0.05
    Expansion
    -0.05
    POSITIVE LOGITS
    suit
    0.08
     suitable
    0.07
     available
    0.07
    alia
    0.07
    ModelError
    0.07
    alary
    0.07
     AVAILABLE
    0.07
    ôm
    0.07
     adequate
    0.07
    Suit
    0.07
    Activations Density 0.039%

    No Known Activations