© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 82327
    Prev
    Next
    INDEX
    Explanations

    phrases related to species classification and genetic analysis

    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
    loff
    -0.07
    ikat
    -0.06
    imb
    -0.06
    ga
    -0.06
     Category
    -0.06
    asures
    -0.06
    åĽ´
    -0.06
    ãĥ³ãĥĨãĤ£
    -0.06
    Accessor
    -0.06
    ipur
    -0.05
    POSITIVE LOGITS
     keyed
    0.07
    voucher
    0.07
    fusc
    0.07
     доÑĤ
    0.07
    antic
    0.07
    okens
    0.07
    enville
    0.06
     synonym
    0.06
    ffield
    0.06
    AffineTransform
    0.06
    Activations Density 0.017%

    No Known Activations