© 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. 77677
    Prev
    Next
    INDEX
    Explanations

    JSON data structures and syntax

    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
    oter
    -0.08
    _anchor
    -0.07
    _VOID
    -0.06
    (mm
    -0.06
    otty
    -0.06
    KC
    -0.06
    ÑģÑĤÑİ
    -0.06
     Gaines
    -0.06
     nye
    -0.06
    окÑĢем
    -0.06
    POSITIVE LOGITS
    idge
    0.07
    irth
    0.06
    üne
    0.06
    amburger
    0.06
    .xz
    0.06
    unas
    0.06
    ucker
    0.06
    CDATA
    0.06
    nest
    0.06
     Lik
    0.06
    Activations Density 0.017%

    No Known Activations