© 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. 119221
    Prev
    Next
    INDEX
    Explanations

    terms related to qualifications and affiliations

    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
    eyi
    -0.09
    _strerror
    -0.08
    essen
    -0.08
    isle
    -0.08
    icular
    -0.07
    eya
    -0.07
    slaught
    -0.07
     Capitals
    -0.07
    opes
    -0.07
    isma
    -0.07
    POSITIVE LOGITS
     owners
    0.08
     owner
    0.06
    -owned
    0.06
    loud
    0.06
     Owners
    0.05
     owned
    0.05
    ÙĦس
    0.05
     plo
    0.05
     cân
    0.05
     Owner
    0.05
    Activations Density 0.001%

    No Known Activations