© 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. 105942
    Prev
    Next
    INDEX
    Explanations

    keywords related to documentation and records

    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
    oks
    -0.07
    olk
    -0.06
     못
    -0.06
     Chapters
    -0.06
    orate
    -0.06
    .mk
    -0.06
     Kes
    -0.06
    eder
    -0.06
    ois
    -0.06
    ARK
    -0.06
    POSITIVE LOGITS
     dated
    0.09
     states
    0.08
     says
    0.08
    states
    0.08
     saying
    0.08
    ãģ«ãĤĪ
    0.07
    dated
    0.07
    .states
    0.07
    ickey
    0.07
     reading
    0.07
    Activations Density 0.039%

    No Known Activations