© 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. 55375
    Prev
    Next
    INDEX
    Explanations

    phrases indicating external locations or contexts

    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
    ickle
    -0.07
    ienne
    -0.07
    ossip
    -0.07
    trap
    -0.07
    shape
    -0.07
    Äĩe
    -0.07
    gewater
    -0.06
    umps
    -0.06
    riage
    -0.06
    indow
    -0.06
    POSITIVE LOGITS
     outside
    0.10
     Outside
    0.08
    outside
    0.08
    Outside
    0.08
    fox
    0.07
    å¤ĸ
    0.07
     external
    0.07
     apart
    0.06
     Pitt
    0.06
    illis
    0.06
    Activations Density 0.006%

    No Known Activations