© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 97862
    Prev
    Next
    INDEX
    Explanations

    components related to technology and interfaces

    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
    voie
    -0.08
    oppable
    -0.08
    ActionCreators
    -0.07
    lator
    -0.07
    é¥Ń
    -0.07
    loom
    -0.07
    OutputStream
    -0.07
    оÑĢÑĭ
    -0.07
    ÙĪص
    -0.07
    mam
    -0.06
    POSITIVE LOGITS
    -muted
    0.07
    666
    0.07
    uder
    0.06
     hel
    0.06
    scape
    0.06
     subordinate
    0.06
    ku
    0.06
    ajs
    0.05
    fu
    0.05
    FU
    0.05
    Activations Density 0.134%

    No Known Activations