© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 2601
    Prev
    Next
    INDEX
    Explanations

    phrases related to strategies for leveraging resources effectively

    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
    jo
    -0.06
    ADS
    -0.06
    UNK
    -0.06
    ndx
    -0.06
     cutoff
    -0.05
    ione
    -0.05
     sum
    -0.05
    ads
    -0.05
    atti
    -0.05
    ry
    -0.05
    POSITIVE LOGITS
     advantage
    0.08
    à¸Ľà¸£à¸°à¹Ĥยà¸Ĭà¸Ļ
    0.07
    usi
    0.07
    instead
    0.07
    use
    0.07
    éĥİ
    0.07
     instead
    0.06
     towards
    0.06
    roe
    0.06
     Äijá»ĥ
    0.06
    Activations Density 0.023%

    No Known Activations