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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 94107
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "one" and related phrases indicating singularity or unity

    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
    endar
    -0.07
     klu
    -0.07
    ulatory
    -0.06
    teri
    -0.06
    _clock
    -0.06
    _dup
    -0.06
    iais
    -0.06
    ulong
    -0.06
    cÃŃ
    -0.05
    anc
    -0.05
    POSITIVE LOGITS
    éĤ£éĩĮ
    0.07
    adle
    0.07
    avra
    0.07
    ürk
    0.07
    947
    0.07
    ilk
    0.06
    ething
    0.06
    adier
    0.06
     Simpsons
    0.06
    ذا
    0.06
    Activations Density 0.005%

    No Known Activations