Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 4657
    Prev
    Next
    INDEX
    Explanations

    phrases indicating scarcity or a limited quantity

    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
    BERS
    -0.07
    uel
    -0.06
    UEL
    -0.06
    gap
    -0.06
    gia
    -0.06
    baz
    -0.06
    laz
    -0.06
    ANDOM
    -0.06
    gio
    -0.06
    çīĪ
    -0.06
    POSITIVE LOGITS
    things
    0.09
     things
    0.09
    /no
    0.08
     other
    0.08
    ever
    0.08
    thing
    0.08
    REGION
    0.07
     ÑħÑĤо
    0.07
     anyone
    0.07
     others
    0.07
    Activations Density 0.007%

    No Known Activations