© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 75795
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives that convey value or quality

    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
    dea
    -0.08
    contri
    -0.08
    ìĽIJìĿ´
    -0.08
    illac
    -0.08
    conj
    -0.08
    endencies
    -0.08
    anca
    -0.08
    stractions
    -0.08
    ingers
    -0.07
    Ñĥже
    -0.07
    POSITIVE LOGITS
     for
    0.07
     although
    0.06
     general
    0.06
    135
    0.06
     fol
    0.06
    ;
    0.06
     followed
    0.06
     Keller
    0.06
     Lopez
    0.06
    228
    0.06
    Activations Density 0.029%

    No Known Activations