© 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. 87699
    Prev
    Next
    INDEX
    Explanations

    references to financial obligations and payments

    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
    æī±
    -0.07
     ÑģÑĤав
    -0.07
    ÙĪÙĦا
    -0.06
     PureComponent
    -0.06
    iss
    -0.06
    elere
    -0.06
    $_['
    -0.06
    à¸µà¸Ľ
    -0.06
    nten
    -0.06
    sembl
    -0.06
    POSITIVE LOGITS
    auce
    0.07
    aise
    0.07
    rone
    0.06
    aic
    0.06
    imuth
    0.06
    iggins
    0.06
     forth
    0.06
    dam
    0.06
    ikon
    0.06
     Hao
    0.06
    Activations Density 0.011%

    No Known Activations