© 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. 77264
    Prev
    Next
    INDEX
    Explanations

    industry-related terms and references

    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
    inkel
    -0.07
    IFIC
    -0.06
    CHANT
    -0.06
    allon
    -0.06
    alette
    -0.06
    .advance
    -0.06
    >>>>
    -0.06
    PDO
    -0.06
    ainty
    -0.06
    ExecutionContext
    -0.06
    POSITIVE LOGITS
    oji
    0.06
    izzly
    0.06
    alk
    0.06
    EMPL
    0.06
    åĸľ
    0.06
    ensburg
    0.06
    TabControl
    0.06
    ZR
    0.06
    ä½ĵèĤ²
    0.06
    ahun
    0.06
    Activations Density 0.000%

    No Known Activations