© 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. 15-LLAMASCOPE-RES-131K
    6. 1241
    Prev
    Next
    INDEX
    Explanations

    statistical significance and mathematical results in research data

    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
    nox
    -0.07
    len
    -0.06
    lop
    -0.06
    loe
    -0.06
    chap
    -0.06
    nowled
    -0.06
    uru
    -0.06
    леÑĤ
    -0.06
    onic
    -0.06
    еÑĪ
    -0.06
    POSITIVE LOGITS
    /=
    0.08
    бÑĥдÑĮ
    0.07
     neust
    0.07
    ÙĬاÙĨ
    0.06
    ylie
    0.06
    ixo
    0.06
    .habbo
    0.06
     Yorker
    0.06
     finan
    0.06
     zda
    0.06
    Activations Density 0.040%

    No Known Activations