© 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. 107191
    Prev
    Next
    INDEX
    Explanations

    references to the "localhost" network address in a technical context

    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
    inand
    -0.08
    orget
    -0.07
    ngle
    -0.07
    éri
    -0.06
     prostitutas
    -0.06
    _LSB
    -0.06
    OURCES
    -0.06
    UDO
    -0.06
    ëģĶ
    -0.06
    ibel
    -0.06
    POSITIVE LOGITS
    ed
    0.09
    /local
    0.08
    .local
    0.08
    -local
    0.07
    utzer
    0.07
    .gdx
    0.07
    i
    0.07
     Tie
    0.07
    s
    0.07
     tie
    0.06
    Activations Density 0.002%

    No Known Activations