© 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. 87270
    Prev
    Next
    INDEX
    Explanations

    phrases related to environmental science or conservation

    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
    aki
    -0.07
    ono
    -0.07
    arity
    -0.06
     prompt
    -0.06
    agra
    -0.06
    emez
    -0.06
    itra
    -0.06
    elan
    -0.06
     Radical
    -0.06
     Morton
    -0.06
    POSITIVE LOGITS
    ĶåĽŀ
    0.06
     Darling
    0.06
    ieber
    0.06
     chrom
    0.06
     desar
    0.06
    ób
    0.06
    ingers
    0.06
     slee
    0.06
    edList
    0.06
     Pols
    0.06
    Activations Density 0.002%

    No Known Activations