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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-131K
    6. 96047
    Prev
    Next
    INDEX
    Explanations

    references to jury decisions and financial awards in legal 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
     Kostenlos
    -0.08
    ìĶ
    -0.07
     Slate
    -0.07
     bát
    -0.07
    EDIA
    -0.07
     ul
    -0.07
    /Branch
    -0.06
    entai
    -0.06
    ueur
    -0.06
    âĻĢ
    -0.06
    POSITIVE LOGITS
    resco
    0.06
    ROP
    0.06
    069
    0.06
    ats
    0.06
    213
    0.06
    aju
    0.06
    atz
    0.06
    ci
    0.06
     Minute
    0.05
    &eacute
    0.05
    Activations Density 0.009%

    No Known Activations