© 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. 124398
    Prev
    Next
    INDEX
    Explanations

    phrases related to bringing or providing something

    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
    angler
    -0.08
    uilt
    -0.07
    ÃŃž
    -0.07
    anton
    -0.07
     knull
    -0.07
    .u
    -0.07
    osaur
    -0.07
    oeff
    -0.06
    ">//
    -0.06
    Periph
    -0.06
    POSITIVE LOGITS
    585
    0.07
     bring
    0.07
    elage
    0.06
    assi
    0.06
    åĪ°
    0.06
    650
    0.06
    098
    0.06
    ymi
    0.06
    abis
    0.06
     cohorts
    0.06
    Activations Density 0.018%

    No Known Activations