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. 29-LLAMASCOPE-MLP-131K
    6. 5077
    Prev
    Next
    INDEX
    Explanations

    terminologies related to media, arts, and customer service

    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
    lew
    -0.06
    ahn
    -0.06
    riba
    -0.06
    aber
    -0.06
    bern
    -0.06
    мена
    -0.06
     fol
    -0.06
    abler
    -0.06
     â̦.
    -0.06
    lege
    -0.06
    POSITIVE LOGITS
    ,
    0.18
    ี,
    0.10
    ,↵
    0.09
    à¹Į,
    0.09
    à¥ĭ,
    0.08
    -,
    0.07
    :,
    0.07
    ा,
    0.07
    ,in
    0.07
    à¥Ģ,
    0.07
    Activations Density 0.343%

    No Known Activations