© 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. 40237
    Prev
    Next
    INDEX
    Explanations

    phrases related to user account actions and management

    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
    _ELEMENTS
    -0.07
    arena
    -0.07
    afort
    -0.06
    Advertisement
    -0.06
    anitize
    -0.06
    istar
    -0.06
    hab
    -0.06
     Runner
    -0.06
    nem
    -0.06
    attery
    -0.06
    POSITIVE LOGITS
     gene
    0.07
    agan
    0.07
     persons
    0.07
    autos
    0.06
    éo
    0.06
    ảo
    0.06
     bub
    0.06
    ork
    0.06
    oi
    0.06
    Persons
    0.06
    Activations Density 0.001%

    No Known Activations