© 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. 15-LLAMASCOPE-RES-131K
    11. 1130
    Prev
    Next
    INDEX
    Explanations

    references to studies or reports related to public health

    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
    çĵ
    -0.08
    .sul
    -0.08
     YEARS
    -0.08
     decade
    -0.07
     decades
    -0.07
     iht
    -0.07
     years
    -0.07
     gerne
    -0.07
    years
    -0.07
     пÑĢеÑģ
    -0.07
    POSITIVE LOGITS
    uning
    0.07
     Ventures
    0.07
     ISSN
    0.07
     initial
    0.06
     early
    0.06
    aths
    0.06
     ventures
    0.06
    amt
    0.06
     data
    0.05
    CLR
    0.05
    Activations Density 0.009%

    No Known Activations