© 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. 75143
    Prev
    Next
    INDEX
    Explanations

    phrases indicating high praise or positive evaluations

    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
    allen
    -0.07
    ezier
    -0.07
    ÅĽnie
    -0.07
    inged
    -0.07
    /we
    -0.06
    PageIndex
    -0.06
     FREE
    -0.06
    loat
    -0.06
    entanyl
    -0.06
     гÑĢн
    -0.06
    POSITIVE LOGITS
    intel
    0.07
     intellectual
    0.07
     Clients
    0.07
    inct
    0.07
     delivery
    0.06
     client
    0.06
     overall
    0.06
    åĪĩ
    0.06
     Depths
    0.06
     sacr
    0.06
    Activations Density 0.001%

    No Known Activations