© 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 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. 118759
    Prev
    Next
    INDEX
    Explanations

    comparative phrases and expressions of capability or performance

    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
    ãģŁãĤī
    -0.06
    licht
    -0.06
    elper
    -0.06
     Burns
    -0.06
    ubit
    -0.06
    ista
    -0.06
    berman
    -0.06
     Bergen
    -0.06
    xac
    -0.06
    поÑĩ
    -0.06
    POSITIVE LOGITS
    alsy
    0.07
    èĦ
    0.07
     its
    0.06
    ÑĸÑĶ
    0.06
    anchors
    0.06
    Anchor
    0.06
    ailable
    0.06
     Cust
    0.06
    ecure
    0.06
    ringe
    0.06
    Activations Density 0.006%

    No Known Activations