© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 3486
    Prev
    Next
    INDEX
    Explanations

    mentions of film festivals and related events

    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
    uling
    -0.07
    zens
    -0.06
    jos
    -0.06
    chants
    -0.06
     needs
    -0.06
     diff
    -0.06
    á»į
    -0.06
    apper
    -0.06
    ius
    -0.06
    à¸Ħล
    -0.06
    POSITIVE LOGITS
     Åŀu
    0.07
     studio
    0.07
    /***/
    0.07
    studio
    0.07
    TRL
    0.07
     hotel
    0.07
     Ryder
    0.07
    æŃ£åľ¨
    0.06
     Äijang
    0.06
     -*-č↵
    0.06
    Activations Density 0.012%

    No Known Activations