© 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. 83580
    Prev
    Next
    INDEX
    Explanations

    specific geographical or location-based references

    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
    oster
    -0.07
    ilage
    -0.07
    zell
    -0.07
    gw
    -0.07
    eon
    -0.07
    _NT
    -0.06
    mil
    -0.06
    idon
    -0.06
    ampie
    -0.06
    \CMS
    -0.06
    POSITIVE LOGITS
     of
    0.06
    erse
    0.06
    atis
    0.06
     Wenger
    0.06
    uing
    0.06
    enger
    0.06
    _matching
    0.05
    atische
    0.05
    αÏĥ
    0.05
    liers
    0.05
    Activations Density 0.000%

    No Known Activations