© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9-LLAMASCOPE-RES-131K
    11. 95093
    Prev
    Next
    INDEX
    Explanations

    references to intellectual property and related legal concepts

    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
     ante
    -0.07
    ibs
    -0.06
     gang
    -0.06
     wit
    -0.06
     with
    -0.06
     per
    -0.06
    oad
    -0.06
    hrad
    -0.06
    >{!!
    -0.05
    ,
    -0.05
    POSITIVE LOGITS
    AILS
    0.08
     Brow
    0.07
    ạnh
    0.07
    enstein
    0.07
    ables
    0.07
    аÑĢÑĮ
    0.07
    sse
    0.06
     Intermediate
    0.06
    vais
    0.06
    bra
    0.06
    Activations Density 0.005%

    No Known Activations