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. 44402
    Prev
    Next
    INDEX
    Explanations

    terms related to consolidation and the merging of entities or resources

    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
    æĸĻ
    -0.07
    arer
    -0.06
    主義
    -0.06
    eer
    -0.06
    ÑĨе
    -0.06
    embro
    -0.06
     Ñģобой
    -0.06
    æĭ©
    -0.06
    riz
    -0.06
    allocator
    -0.06
    POSITIVE LOGITS
    ated
    0.11
    idine
    0.10
    olid
    0.09
    ignment
    0.08
    iction
    0.07
    ATED
    0.07
     Appropri
    0.07
    ating
    0.07
     Consolid
    0.07
     Revenue
    0.07
    Activations Density 0.004%

    No Known Activations