© 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. 83543
    Prev
    Next
    INDEX
    Explanations

    opening phrases or quotations that suggest dialogue or narration

    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
    dech
    -0.10
    صاÙĦ
    -0.09
     Ãľl
    -0.08
    jee
    -0.08
    ibase
    -0.08
    IEW
    -0.08
    ault
    -0.07
    lıģına
    -0.07
     Шев
    -0.07
    FTER
    -0.07
    POSITIVE LOGITS
    ours
    0.06
    "
    0.06
    atak
    0.06
     "
    0.06
    ,
    0.06
    itti
    0.05
    uyo
    0.05
     and
    0.05
     Dj
    0.05
     Organic
    0.05
    Activations Density 0.026%

    No Known Activations