© 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. 9-LLAMASCOPE-RES-131K
    11. 97827
    Prev
    Next
    INDEX
    Explanations

    references to calls to action with contact 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
    er
    -0.06
    is
    -0.06
    erton
    -0.06
    inis
    -0.06
    iz
    -0.06
    beit
    -0.06
    trade
    -0.05
     correctness
    -0.05
    iam
    -0.05
    ided
    -0.05
    POSITIVE LOGITS
    bjerg
    0.08
    esson
    0.08
    essler
    0.07
    odef
    0.07
     suite
    0.07
    efined
    0.07
    orts
    0.07
    ctrl
    0.07
    abeth
    0.06
     sqr
    0.06
    Activations Density 0.004%

    No Known Activations