© 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. 82809
    Prev
    Next
    INDEX
    Explanations

    affirmations of repair capabilities and the range of services offered

    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
     sleep
    -0.07
    kyt
    -0.07
     tinh
    -0.06
    rego
    -0.06
     mattress
    -0.06
    ÃŃo
    -0.06
    .cloud
    -0.06
     couch
    -0.06
    alten
    -0.06
     Lawn
    -0.06
    POSITIVE LOGITS
     Cul
    0.09
    .gf
    0.08
     kitchen
    0.08
    好äºĨ
    0.07
     Kitchen
    0.07
    rtl
    0.07
    radi
    0.07
    Kitchen
    0.07
    BBBB
    0.06
    itness
    0.06
    Activations Density 0.001%

    No Known Activations