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

    Neuronpedia

    APICircuit 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. 22-LLAMASCOPE-RES-131K
    6. 5518
    Prev
    Next
    INDEX
    Explanations

    key points, criteria, and structured lists or steps within the text

    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
    UNUSED
    -0.07
     (↵↵
    -0.07
    िà¤Ĺ
    -0.07
    ̧
    -0.06
    vertise
    -0.06
    ilip
    -0.06
     Crushers
    -0.06
    isset
    -0.06
    irt
    -0.06
    ĶåĽŀ
    -0.06
    POSITIVE LOGITS
    :↵
    0.24
    :↵↵
    0.20
     :↵
    0.18
    :č↵
    0.17
    ):↵
    0.16
    ï¼ļ↵
    0.16
    ():↵
    0.15
     :↵↵
    0.15
    ]:↵
    0.15
    :</
    0.15
    Activations Density 0.086%

    No Known Activations