© 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. 125300
    Prev
    Next
    INDEX
    Explanations

    terms related to web development technologies and coding

    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
    Ui
    -0.07
    lineEdit
    -0.07
    /goto
    -0.07
    -await
    -0.07
    ozem
    -0.07
    .annot
    -0.07
    kbd
    -0.06
     célib
    -0.06
    rax
    -0.06
    ustum
    -0.06
    POSITIVE LOGITS
    508
    0.07
     Casc
    0.07
     Web
    0.07
     structural
    0.07
    _equiv
    0.06
     standards
    0.06
    sic
    0.06
    ntl
    0.06
    alary
    0.06
    .dtd
    0.06
    Activations Density 0.004%

    No Known Activations