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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 118330
    Prev
    Next
    INDEX
    Explanations

    expectation statements or assertions related to programming tests

    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
    áºŃy
    -0.07
    ques
    -0.06
    ohn
    -0.06
     hero
    -0.06
    ÑģÑĤан
    -0.06
    orts
    -0.06
     Fork
    -0.06
     Artem
    -0.06
    afil
    -0.06
    hero
    -0.06
    POSITIVE LOGITS
    uent
    0.07
    675
    0.07
    онÑĮ
    0.07
    ÏĦικ
    0.06
    gment
    0.06
    Warn
    0.06
    IFICATE
    0.06
    ÂłkW
    0.06
    ÃIJ
    0.06
     RuntimeObject
    0.06
    Activations Density 0.006%

    No Known Activations