© 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. 15-LLAMASCOPE-RES-131K
    6. 103795
    Prev
    Next
    INDEX
    Explanations

    phrases related to eligibility and requirements for certain programs or benefits

    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
     Stranger
    -0.08
    elder
    -0.08
    enties
    -0.07
    elli
    -0.07
     Innoc
    -0.07
    udit
    -0.07
    å°ĸ
    -0.07
    ailles
    -0.06
     stranger
    -0.06
    este
    -0.06
    POSITIVE LOGITS
     individuals
    0.09
     anyone
    0.07
    392
    0.07
    487
    0.07
    اØ
    0.06
    485
    0.06
    663
    0.06
     person
    0.06
    ãģijãĤĮãģ©
    0.06
     PROCUREMENT
    0.06
    Activations Density 0.081%

    No Known Activations