© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 16296
    Prev
    Next
    INDEX
    Explanations

    references to news organizations and media outlets

    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
    oret
    -0.07
    umber
    -0.06
    annonce
    -0.06
     gate
    -0.06
    iem
    -0.06
    ags
    -0.06
    gate
    -0.06
    orp
    -0.06
    .toArray
    -0.06
    ÅĤem
    -0.06
    POSITIVE LOGITS
     rằng
    0.08
     there
    0.07
     that
    0.07
    ernals
    0.07
     bahwa
    0.07
    ÏĦι
    0.07
    [sizeof
    0.07
    aversal
    0.07
    istry
    0.06
    Brains
    0.06
    Activations Density 0.014%

    No Known Activations