© 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. 15-LLAMASCOPE-RES-131K
    11. 27617
    Prev
    Next
    INDEX
    Explanations

    concepts related to important events and their significance

    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
    049
    -0.07
    948
    -0.06
    scopes
    -0.06
     otherwise
    -0.06
    /DTD
    -0.06
     scopes
    -0.06
     defe
    -0.06
    romatic
    -0.06
     maneuver
    -0.06
     patch
    -0.06
    POSITIVE LOGITS
    orthand
    0.07
    æĤ£
    0.07
    Caller
    0.06
    اÙĤ
    0.06
     protocol
    0.06
    ecal
    0.06
    .scalablytyped
    0.06
    IBUT
    0.06
    åĨł
    0.06
    ryn
    0.06
    Activations Density 0.025%

    No Known Activations