© 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. 76395
    Prev
    Next
    INDEX
    Explanations

    phrases related to membership and eligibility criteria

    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
    BYTES
    -0.07
    _RT
    -0.07
    isay
    -0.07
    gratis
    -0.06
    olson
    -0.06
    otta
    -0.06
     TÆ°
    -0.06
    ives
    -0.06
     Landing
    -0.06
     Placement
    -0.06
    POSITIVE LOGITS
     Household
    0.08
     registered
    0.07
     household
    0.07
    registered
    0.07
     listed
    0.07
     signed
    0.07
    ownership
    0.07
     ownership
    0.06
    ysqli
    0.06
    996
    0.06
    Activations Density 0.025%

    No Known Activations