© 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. 126586
    Prev
    Next
    INDEX
    Explanations

    numerical ratings associated with performances or events

    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
    illery
    -0.08
    forward
    -0.07
    ohana
    -0.07
    flix
    -0.07
     Term
    -0.07
    olulu
    -0.07
    _palette
    -0.07
    ammo
    -0.06
    osaur
    -0.06
    адж
    -0.06
    POSITIVE LOGITS
    rol
    0.06
    91
    0.06
     pcl
    0.06
    .exe
    0.05
     Ger
    0.05
    0
    0.05
     oy
    0.05
    406
    0.05
     overhead
    0.05
     theirs
    0.05
    Activations Density 0.001%

    No Known Activations