© 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. 62254
    Prev
    Next
    INDEX
    Explanations

    details related to magazine contributions and submissions

    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
     sh
    -0.06
     ear
    -0.06
    ear
    -0.06
    1
    -0.06
    ..
    -0.06
     publicly
    -0.05
     Ear
    -0.05
     prob
    -0.05
    ona
    -0.05
     repeat
    -0.05
    POSITIVE LOGITS
    .FontStyle
    0.10
     jadx
    0.09
    exels
    0.09
    adel
    0.09
    .scalablytyped
    0.08
     putas
    0.08
    taboola
    0.08
    è´£
    0.08
    Printing
    0.08
    andel
    0.08
    Activations Density 0.002%

    No Known Activations