Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 106692
    Prev
    Next
    INDEX
    Explanations

    references to miscellaneous items or additional information

    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
    (es
    -0.07
    ebin
    -0.07
    witch
    -0.07
    ÑĢог
    -0.06
    ÙĤت
    -0.06
    loo
    -0.06
    aret
    -0.06
    essed
    -0.06
    buster
    -0.06
    bourg
    -0.06
    POSITIVE LOGITS
     alike
    0.09
    /etc
    0.08
    :len
    0.06
    jar
    0.06
     Lowe
    0.06
    ãģ«ãĤĪãĤĭ
    0.06
    lying
    0.06
    eter
    0.06
    afür
    0.06
    Chr
    0.06
    Activations Density 0.016%

    No Known Activations