© 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. 17-LLAMASCOPE-RES-131K
    11. 125722
    Prev
    Next
    INDEX
    Explanations

    complex mathematical constructs and descriptions involving sets and inequalities

    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
    atas
    -0.06
    .tw
    -0.06
    LogLevel
    -0.06
    andin
    -0.06
    butt
    -0.06
    ad
    -0.06
    λήÏĤ
    -0.06
     invit
    -0.06
     ActionTypes
    -0.06
    armac
    -0.05
    POSITIVE LOGITS
     den
    0.18
    den
    0.17
    -den
    0.13
     Den
    0.12
    Den
    0.11
     DEN
    0.11
     abbreviated
    0.11
    =:
    0.10
    abbrev
    0.10
     designated
    0.10
    Activations Density 0.216%

    No Known Activations