© 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. 131046
    Prev
    Next
    INDEX
    Explanations

    terms related to literalness or factual interpretations

    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
    ÅĤo
    -0.08
    emann
    -0.07
    onet
    -0.07
    ÑģÑı
    -0.07
    egg
    -0.07
    eler
    -0.07
    yonel
    -0.07
    esel
    -0.07
    arde
    -0.07
    istrovstvÃŃ
    -0.07
    POSITIVE LOGITS
    mente
    0.14
    ized
    0.11
    izing
    0.10
    -minded
    0.10
    ity
    0.09
     же
    0.08
     minded
    0.08
    ize
    0.08
    ization
    0.08
    ities
    0.08
    Activations Density 0.008%

    No Known Activations