© 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. 15382
    Prev
    Next
    INDEX
    Explanations

    references to people, communities, and the impact of initiatives on their lives

    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
    ame
    -0.06
    icio
    -0.06
    AME
    -0.06
     barg
    -0.06
    mia
    -0.06
    piel
    -0.06
    immel
    -0.06
     Gä
    -0.06
    du
    -0.06
    umlu
    -0.06
    POSITIVE LOGITS
    opot
    0.08
    olik
    0.07
    rze
    0.07
    GuidId
    0.07
    @c
    0.07
    Ð¡Ðł
    0.07
    é±
    0.07
    CompatActivity
    0.07
    HeaderCode
    0.07
    /Error
    0.06
    Activations Density 0.020%

    No Known Activations