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. 31-LLAMASCOPE-RES-131K
    6. 44164
    Prev
    Next
    INDEX
    Explanations

    programming constructs and method definitions in code

    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
    =null
    -0.06
     downstream
    -0.06
    OST
    -0.06
    _PARAMETERS
    -0.06
    null
    -0.06
    >null
    -0.06
    ________________________________
    -0.05
    *&
    -0.05
    deen
    -0.05
    LAR
    -0.05
    POSITIVE LOGITS
     YES
    0.20
    YES
    0.17
     NO
    0.17
    :YES
    0.16
    :NO
    0.14
    NO
    0.14
     Yes
    0.13
    (NO
    0.13
    =YES
    0.13
    Yes
    0.12
    Activations Density 0.008%

    No Known Activations