© 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. 106361
    Prev
    Next
    INDEX
    Explanations

    mathematical statements involving conditions or constraints

    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
    SError
    -0.08
     ков
    -0.08
    uria
    -0.07
    ırak
    -0.07
    BuilderInterface
    -0.07
     antis
    -0.07
    ÏĢε
    -0.07
    _SB
    -0.07
    ennes
    -0.06
    %@",
    -0.06
    POSITIVE LOGITS
    :↵
    0.07
    ushman
    0.06
    eid
    0.06
    å¹¹ç·ļ
    0.06
     both
    0.06
    chaft
    0.06
    oty
    0.06
    ighton
    0.06
    ĩ
    0.05
     BOTH
    0.05
    Activations Density 0.077%

    No Known Activations