© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 125492
    Prev
    Next
    INDEX
    Explanations

    phrases related to obligations, responsibilities, and varying levels of service or product offerings

    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
    prech
    -0.07
    /static
    -0.07
    offsetof
    -0.07
    _ASCII
    -0.07
    _minimum
    -0.07
     merc
    -0.07
    ëĤ
    -0.07
    FromBody
    -0.06
    ACEMENT
    -0.06
    ëijĺ
    -0.06
    POSITIVE LOGITS
     ones
    0.09
     complex
    0.09
     large
    0.08
     larg
    0.08
     Complex
    0.07
     full
    0.07
     complicated
    0.07
     fully
    0.07
    hi
    0.07
    complex
    0.07
    Activations Density 0.017%

    No Known Activations