© 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. 4107
    Prev
    Next
    INDEX
    Explanations

    technical specifications and product information related to electronics, specifically laptops and their components

    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
    ÏĤ
    -0.09
     of
    -0.07
    s
    -0.07
     and
    -0.07
    X
    -0.06
    ials
    -0.06
    es
    -0.06
    rey
    -0.06
     ÑģÑĤаÑĢи
    -0.06
    ubs
    -0.06
    POSITIVE LOGITS
    chter
    0.08
    elden
    0.08
    NullException
    0.08
    ault
    0.07
    _userdata
    0.07
    BootApplication
    0.07
    panse
    0.07
    ABCDEFG
    0.07
    usercontent
    0.07
     sobie
    0.07
    Activations Density 0.098%

    No Known Activations