© 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. 17-LLAMASCOPE-RES-131K
    6. 77628
    Prev
    Next
    INDEX
    Explanations

    specific titles and release dates of artistic works or media

    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
    ostel
    -0.07
    sterol
    -0.07
     Ãľn
    -0.07
    æ¼
    -0.07
    aggi
    -0.06
    nees
    -0.06
    à¸ķะ
    -0.06
    vsp
    -0.06
    rosso
    -0.06
    .cz
    -0.06
    POSITIVE LOGITS
    ë§ī
    0.07
    ocker
    0.07
     Bale
    0.07
     sẵn
    0.06
     Fist
    0.06
    actionDate
    0.06
    ìĹ¼
    0.06
    ONTAL
    0.06
    ReadStream
    0.06
    zbollah
    0.06
    Activations Density 0.028%

    No Known Activations