© 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 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. 86113
    Prev
    Next
    INDEX
    Explanations

    citation information in academic writing

    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
    .scalablytyped
    -0.09
    iena
    -0.07
    rong
    -0.07
    vron
    -0.07
    autop
    -0.07
    ragen
    -0.07
    ARGE
    -0.07
    Ùĥار
    -0.06
    DebugEnabled
    -0.06
    ongs
    -0.06
    POSITIVE LOGITS
    ican
    0.06
    eland
    0.06
    ehir
    0.06
    ucks
    0.06
    ixa
    0.05
     Matte
    0.05
    392
    0.05
     ElseIf
    0.05
    igt
    0.05
    igh
    0.05
    Activations Density 0.001%

    No Known Activations