© 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. 125934
    Prev
    Next
    INDEX
    Explanations

    various forms of financial aid and programs aimed at supporting literacy and education

    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
     exter
    -0.07
    ÏĢα
    -0.07
    inke
    -0.07
    intree
    -0.06
    ensch
    -0.06
    ako
    -0.06
     lead
    -0.06
    ritt
    -0.06
    PIO
    -0.06
     Ratings
    -0.06
    POSITIVE LOGITS
     households
    0.07
     Universal
    0.07
     proposal
    0.07
     pilot
    0.07
     distrib
    0.07
     Maur
    0.06
     universal
    0.06
     univers
    0.06
     cash
    0.06
     unconditional
    0.06
    Activations Density 0.003%

    No Known Activations