© 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. 70752
    Prev
    Next
    INDEX
    Explanations

    instances of colons, indicating lists or important points in the text

    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
    Ñİк
    -0.07
    rych
    -0.07
    _IDENT
    -0.07
    vider
    -0.07
    èĭĹ
    -0.06
    åĦ¿
    -0.06
    åħĴ
    -0.06
    STDOUT
    -0.06
    Ñģли
    -0.06
     à¤ıड
    -0.06
    POSITIVE LOGITS
    ument
    0.06
     TextAlign
    0.06
    uat
    0.06
    253
    0.06
    ILED
    0.06
    ĶĦ
    0.06
     Riley
    0.06
    chw
    0.06
    ifa
    0.06
    erty
    0.06
    Activations Density 0.001%

    No Known Activations