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. 71233
    Prev
    Next
    INDEX
    Explanations

    phrases that express positive developments or achievements

    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
    inkel
    -0.07
    entiful
    -0.07
    offsetof
    -0.07
    :variables
    -0.06
     kred
    -0.06
    471
    -0.06
    idis
    -0.06
    edList
    -0.06
    agua
    -0.06
    rote
    -0.06
    POSITIVE LOGITS
     exciting
    0.08
     opportunity
    0.07
     step
    0.07
    plex
    0.07
     stride
    0.07
     example
    0.06
     moment
    0.06
     occasion
    0.06
    iban
    0.06
     milestone
    0.06
    Activations Density 0.023%

    No Known Activations