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. 9-LLAMASCOPE-RES-131K
    6. 96039
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to conditions and limitations

    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
     ↵↵
    -0.07
    ancellable
    -0.07
    åĽ²
    -0.07
    鼶
    -0.07
    reur
    -0.07
    .nlm
    -0.07
     inout
    -0.06
     pf
    -0.06
    zac
    -0.06
    axy
    -0.06
    POSITIVE LOGITS
    sett
    0.07
    atron
    0.07
    rops
    0.07
    -в
    0.06
    wel
    0.06
    UsageId
    0.06
     Mac
    0.06
    ateria
    0.06
     Fallon
    0.06
     FactoryBot
    0.06
    Activations Density 0.025%

    No Known Activations