© 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. 128903
    Prev
    Next
    INDEX
    Explanations

    occurrences of the prefix "uns," indicating negation or absence

    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
    zin
    -0.09
    zan
    -0.08
    ervo
    -0.08
    etic
    -0.08
    SYNC
    -0.07
    baÅŁ
    -0.07
    zd
    -0.07
    hop
    -0.07
    hs
    -0.07
    aver
    -0.07
    POSITIVE LOGITS
     uns
    0.08
     Uns
    0.08
    d
    0.08
    utom
    0.07
    ar
    0.07
    y
    0.06
    ا
    0.06
    paring
    0.06
    air
    0.06
    ward
    0.06
    Activations Density 0.006%

    No Known Activations