© 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. 15-LLAMASCOPE-RES-131K
    11. 88817
    Prev
    Next
    INDEX
    Explanations

    terms related to astrophysics, specifically those associated with black holes and their properties

    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
    agy
    -0.10
    abi
    -0.07
     Cre
    -0.06
    SetTitle
    -0.06
    lates
    -0.06
    arging
    -0.06
    (Gravity
    -0.06
    land
    -0.06
     Sleeping
    -0.06
     Trace
    -0.06
    POSITIVE LOGITS
    ÏĦοÏħ
    0.07
    _MISC
    0.07
    zilla
    0.07
    alo
    0.06
    dzi
    0.06
    .ci
    0.06
    ottie
    0.06
     åł
    0.06
     VÅ©
    0.06
    Łèĥ½
    0.06
    Activations Density 0.025%

    No Known Activations