© 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. 17-LLAMASCOPE-RES-131K
    11. 61391
    Prev
    Next
    INDEX
    Explanations

    references to software or code-related entities and frameworks

    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
    ena
    -0.07
    ohn
    -0.06
    een
    -0.06
    mini
    -0.06
     Moj
    -0.06
    eam
    -0.06
     Armed
    -0.06
     Duch
    -0.06
    ·
    -0.05
    ait
    -0.05
    POSITIVE LOGITS
    conexao
    0.07
    fos
    0.07
    sed
    0.07
    antro
    0.07
    .production
    0.07
    ãĤĵãģ¨
    0.07
    icontrol
    0.07
    _vect
    0.07
    sÃŃ
    0.07
    UPPORTED
    0.07
    Activations Density 0.002%

    No Known Activations