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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 78480
    Prev
    Next
    INDEX
    Explanations

    brackets and references to sections within a document

    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
    ason
    -0.07
    asons
    -0.06
    eniable
    -0.06
     Elo
    -0.06
    erea
    -0.06
     whistle
    -0.06
     carrying
    -0.06
    ophon
    -0.06
    vo
    -0.06
    ida
    -0.06
    POSITIVE LOGITS
    aucoup
    0.08
    ziej
    0.07
    Äįan
    0.07
    erate
    0.07
    843
    0.07
    utow
    0.07
    paged
    0.07
    inclu
    0.07
    HostException
    0.07
    BootTest
    0.07
    Activations Density 0.007%

    No Known Activations