© 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. 56528
    Prev
    Next
    INDEX
    Explanations

    terms related to education and academic performance

    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
    lech
    -0.08
    angered
    -0.07
    ERGY
    -0.07
    ÐķÐł
    -0.07
    jte
    -0.06
    ÑģÑĤÑİ
    -0.06
    /Area
    -0.06
    adir
    -0.06
     Chron
    -0.06
    rupa
    -0.06
    POSITIVE LOGITS
     season
    0.08
    ime
    0.07
     cycle
    0.07
    lg
    0.06
     period
    0.06
    IME
    0.06
     annum
    0.06
     periodo
    0.06
     Holmes
    0.06
    amy
    0.06
    Activations Density 0.010%

    No Known Activations