© 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. 56116
    Prev
    Next
    INDEX
    Explanations

    references to specific locations or addresses

    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
    zik
    -0.08
    æ³ī
    -0.08
    zell
    -0.08
     hã
    -0.08
    deaux
    -0.08
    self
    -0.07
    EFAULT
    -0.07
    κÎŃ
    -0.07
    ÑĤÑĮ
    -0.07
    duino
    -0.07
    POSITIVE LOGITS
    -long
    0.07
    illance
    0.07
    ader
    0.06
    asure
    0.06
    edge
    0.06
    asions
    0.06
    ution
    0.06
     gang
    0.06
    kil
    0.06
    iac
    0.06
    Activations Density 0.006%

    No Known Activations