© 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. 105916
    Prev
    Next
    INDEX
    Explanations

    technical terms and values related to finance and mathematics

    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
    asco
    -0.07
    ArgumentException
    -0.07
    mino
    -0.07
    覧
    -0.07
    igid
    -0.07
    esub
    -0.07
    orners
    -0.06
    imal
    -0.06
     Outside
    -0.06
    Outside
    -0.06
    POSITIVE LOGITS
     middle
    0.16
     central
    0.14
     centre
    0.13
    à¸ģลาà¸ĩ
    0.13
     mid
    0.13
     Central
    0.13
    middle
    0.13
     center
    0.13
     Middle
    0.12
    central
    0.12
    Activations Density 0.034%

    No Known Activations