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. 77287
    Prev
    Next
    INDEX
    Explanations

    specifics related to attributes, roles, and classifications within a context

    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
    wand
    -0.07
    orque
    -0.07
    oram
    -0.07
    ammen
    -0.07
    RenderingContext
    -0.07
     dong
    -0.06
    ammo
    -0.06
    mav
    -0.06
    ambi
    -0.06
    /reference
    -0.06
    POSITIVE LOGITS
     Ratings
    0.08
     ratings
    0.07
     crew
    0.07
     stagger
    0.07
     hull
    0.06
     deck
    0.06
    crew
    0.06
    åħ¸
    0.06
    ratings
    0.06
     rating
    0.06
    Activations Density 0.001%

    No Known Activations