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. MLP Out
    5. 25-LLAMASCOPE-MLP-131K
    6. 72550
    Prev
    Next
    INDEX
    Explanations

    elements related to music charts and performance metrics

    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
    .opend
    -0.08
    ahir
    -0.08
    UCH
    -0.07
    EG
    -0.07
     chez
    -0.06
    enant
    -0.06
    èĬĿ
    -0.06
    agen
    -0.06
    -Line
    -0.06
    uchi
    -0.06
    POSITIVE LOGITS
    iss
    0.08
    acy
    0.07
    arl
    0.07
    ãĥ£
    0.07
    ar
    0.07
    ertia
    0.07
     rein
    0.07
    ise
    0.06
     dys
    0.06
     hol
    0.06
    Activations Density 0.246%

    No Known Activations