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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 22-LLAMASCOPE-RES-131K
    6. 5346
    Prev
    Next
    INDEX
    Explanations

    references to decision-making and consequences

    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
    ãģªãģĮãĤī
    -0.08
    елем
    -0.07
    treeview
    -0.07
    ãģ§ãģĹãĤĩãģĨ
    -0.07
    ãĥ³ãĥĩ
    -0.07
     Sort
    -0.07
     kurulan
    -0.07
    .digital
    -0.07
    ÅĻes
    -0.07
     kullanılan
    -0.07
    POSITIVE LOGITS
     which
    0.43
    which
    0.36
     Which
    0.33
     WHICH
    0.32
    Which
    0.31
    .which
    0.24
     wich
    0.24
    (which
    0.21
     οÏĢοίο
    0.21
     cui
    0.20
    Activations Density 0.415%

    No Known Activations