© 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. 57643
    Prev
    Next
    INDEX
    Explanations

    references to logging frameworks and job management in programming

    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
    oggle
    -0.06
    lop
    -0.06
    üre
    -0.06
    zim
    -0.06
     lob
    -0.05
     Nah
    -0.05
    avor
    -0.05
     tube
    -0.05
    etro
    -0.05
    lim
    -0.05
    POSITIVE LOGITS
    isoft
    0.08
    ownt
    0.07
    ï¸
    0.07
    594
    0.07
     pit
    0.07
    θα
    0.07
     Javier
    0.07
    763
    0.07
    reich
    0.07
    ضÙĦ
    0.07
    Activations Density 0.000%

    No Known Activations