© 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. 17-LLAMASCOPE-RES-131K
    11. 15488
    Prev
    Next
    INDEX
    Explanations

    numerical values associated with references or citations

    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
    ero
    -0.07
    oor
    -0.07
    еÑĢо
    -0.07
    hil
    -0.07
    eru
    -0.07
    égor
    -0.07
    áv
    -0.07
    tero
    -0.06
    IODevice
    -0.06
    .AutoSizeMode
    -0.06
    POSITIVE LOGITS
    vale
    0.07
     Probe
    0.06
     probe
    0.06
    .scalablytyped
    0.06
    .builders
    0.06
    agram
    0.06
    ีว
    0.06
    Ľi
    0.06
     rele
    0.06
     granite
    0.06
    Activations Density 0.022%

    No Known Activations