© 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. 125992
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to membership benefits in a loyalty program

    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
     imported
    -0.07
    _exports
    -0.07
     Ness
    -0.07
    licht
    -0.06
    orsi
    -0.06
    Ordered
    -0.06
    okit
    -0.06
    bubble
    -0.06
    osi
    -0.06
    imon
    -0.06
    POSITIVE LOGITS
     recip
    0.09
     mutual
    0.09
     joint
    0.08
    joint
    0.08
     partner
    0.07
     Partner
    0.07
     reciprocal
    0.07
    ember
    0.07
    ipro
    0.07
     member
    0.07
    Activations Density 0.002%

    No Known Activations