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. 43475
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols or notation

    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
     heartbreaking
    -0.07
    Advertisement
    -0.06
     horrible
    -0.06
     noh
    -0.06
     kombin
    -0.06
    inka
    -0.06
    леÑĩ
    -0.06
    Âļ
    -0.06
    regist
    -0.06
    urai
    -0.06
    POSITIVE LOGITS
     whilst
    0.11
     Humans
    0.11
     Humanity
    0.10
     Whilst
    0.09
     Human
    0.09
     :-↵
    0.09
     Behaviour
    0.08
     Conscious
    0.08
     Homo
    0.08
     endeavour
    0.08
    Activations Density 0.007%

    No Known Activations