© 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. 80381
    Prev
    Next
    INDEX
    Explanations

    mentions of noise in various contexts related to auditory environments

    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
    uja
    -0.09
    acy
    -0.08
    reno
    -0.07
    mor
    -0.07
    ожеÑĤ
    -0.07
    .deepcopy
    -0.07
    most
    -0.07
    ships
    -0.07
    shaw
    -0.07
    oria
    -0.07
    POSITIVE LOGITS
    lessly
    0.09
    less
    0.07
    balls
    0.06
    ÌĪ
    0.06
     pollution
    0.06
    letters
    0.06
    proof
    0.06
     Bun
    0.06
    letes
    0.06
     helmet
    0.06
    Activations Density 0.011%

    No Known Activations