© 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. 93801
    Prev
    Next
    INDEX
    Explanations

    references to thresholds and limits related to measurements or performance metrics

    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
    akis
    -0.07
    emey
    -0.07
    orang
    -0.07
    UILDER
    -0.07
     Lair
    -0.07
    ä»°
    -0.07
    -scalable
    -0.07
    onda
    -0.07
     Checked
    -0.07
    shan
    -0.07
    POSITIVE LOGITS
     target
    0.08
     targets
    0.06
     goal
    0.06
     recommended
    0.06
     previous
    0.06
     targeted
    0.06
     stated
    0.06
    ambre
    0.06
     expected
    0.06
    rosse
    0.06
    Activations Density 0.027%

    No Known Activations