© 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. 73309
    Prev
    Next
    INDEX
    Explanations

    special characters, symbols, or formatting elements

    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
    ses
    -0.07
    Directive
    -0.07
    ways
    -0.06
    oral
    -0.06
    ieder
    -0.06
     Tender
    -0.06
    ingu
    -0.06
    verte
    -0.06
    orch
    -0.06
    ĨĴ
    -0.05
    POSITIVE LOGITS
    nbsp
    0.15
    amp
    0.14
    emsp
    0.13
    apos
    0.11
    ZeroWidthSpace
    0.10
    lt
    0.10
    quot
    0.09
    athers
    0.09
    ersen
    0.09
    iw
    0.09
    Activations Density 0.076%

    No Known Activations