© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 119397
    Prev
    Next
    INDEX
    Explanations

    mentions of downloadable content or wallpapers

    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
    ãng
    -0.07
    cola
    -0.06
    rtl
    -0.06
    ornment
    -0.06
    utar
    -0.06
    ildo
    -0.06
     tal
    -0.06
    atro
    -0.06
    SEA
    -0.06
    ertino
    -0.05
    POSITIVE LOGITS
    BuilderInterface
    0.08
    NewProp
    0.07
    ToProps
    0.07
    stu
    0.07
     wides
    0.07
    .scalablytyped
    0.07
    ONSE
    0.07
    iox
    0.07
     ########.
    0.07
    .Handled
    0.06
    Activations Density 0.001%

    No Known Activations