© 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. 16701
    Prev
    Next
    INDEX
    Explanations

    phrases related to water access and quality issues

    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
     Horton
    -0.07
     Schmidt
    -0.07
    elt
    -0.06
    odnÃŃ
    -0.06
    ROUGH
    -0.06
    pell
    -0.06
     Nack
    -0.06
    asl
    -0.06
    uja
    -0.06
    legation
    -0.06
    POSITIVE LOGITS
    omen
    0.07
    ارس
    0.07
     demean
    0.06
    uito
    0.06
    _CLR
    0.06
    eneral
    0.06
    .dirty
    0.06
    xfff
    0.06
     gere
    0.06
     Accred
    0.06
    Activations Density 0.016%

    No Known Activations