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

    Neuronpedia

    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. 40005
    Prev
    Next
    INDEX
    Explanations

    HTML anchor tags and their attributes

    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
    ationToken
    -0.07
     Depths
    -0.07
    amy
    -0.07
    .scalablytyped
    -0.07
     dilig
    -0.07
    ÄIJT
    -0.07
     COPYING
    -0.07
    rvé
    -0.07
    ãĥ©ãĥ³ãĥī
    -0.07
    entar
    -0.07
    POSITIVE LOGITS
    acob
    0.07
    umm
    0.06
     fist
    0.06
    Âł
    0.06
    ahren
    0.06
    459
    0.05
    .overlay
    0.05
    <small
    0.05
    ogue
    0.05
    apse
    0.05
    Activations Density 0.012%

    No Known Activations