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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B
    4. MLP Out
    5. 25-LLAMASCOPE-MLP-131K
    6. 72583
    Prev
    Next
    INDEX
    Explanations

    occurrences of the phrase "in for" within various 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
    elles
    -0.06
    μαÏĦα
    -0.06
    znik
    -0.06
    subcategory
    -0.06
     sorry
    -0.06
    165
    -0.06
    sein
    -0.06
    etter
    -0.05
    _locator
    -0.05
    venues
    -0.05
    POSITIVE LOGITS
    AU
    0.07
    éf
    0.07
     ilma
    0.07
    rawer
    0.07
     Counts
    0.06
    akin
    0.06
    orsi
    0.06
     counting
    0.06
    oola
    0.06
    alar
    0.06
    Activations Density 0.005%

    No Known Activations