© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 70748
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistical comparisons

    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
     bergen
    -0.07
    elman
    -0.07
    lien
    -0.07
    /Instruction
    -0.06
    ãģĭãĤĬ
    -0.06
    Ware
    -0.06
    ado
    -0.06
    æ³Ĭ
    -0.05
    inson
    -0.05
    illa
    -0.05
    POSITIVE LOGITS
    λÏī
    0.07
     ofType
    0.07
     Bannon
    0.07
     أبÙĬ
    0.07
    ROUGH
    0.07
    ossed
    0.07
    ativ
    0.06
    .raises
    0.06
    HOOK
    0.06
     subrange
    0.06
    Activations Density 0.019%

    No Known Activations