© 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. 69567
    Prev
    Next
    INDEX
    Explanations

    terms related to free or affordable events open to the public

    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
    ult
    -0.07
    ot
    -0.06
     priced
    -0.06
     Deposit
    -0.06
    255
    -0.06
    sym
    -0.06
     Kv
    -0.06
     Su
    -0.06
    236
    -0.06
    ans
    -0.06
    POSITIVE LOGITS
     simply
    0.10
     merely
    0.09
    resa
    0.08
    Gratis
    0.08
     simplement
    0.08
    oux
    0.07
    addtogroup
    0.07
    prit
    0.07
    Simply
    0.07
    beer
    0.07
    Activations Density 0.014%

    No Known Activations