© 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. 117062
    Prev
    Next
    INDEX
    Explanations

    terms related to evidence and documentation requirements

    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
    isol
    -0.08
    iten
    -0.07
    aida
    -0.06
    ue
    -0.06
     Folk
    -0.06
     знаком
    -0.06
     xtype
    -0.06
    iker
    -0.06
    atten
    -0.06
    kor
    -0.06
    POSITIVE LOGITS
     evidence
    0.07
    ivant
    0.07
    dated
    0.07
    documento
    0.07
     att
    0.06
     satisfactory
    0.06
     proof
    0.06
    ncpy
    0.06
    orsche
    0.06
    opher
    0.06
    Activations Density 0.013%

    No Known Activations