© 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. 15-LLAMASCOPE-RES-131K
    11. 1070
    Prev
    Next
    INDEX
    Explanations

    code-related terms and elements within a programming context

    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
    ustom
    -0.07
    ndern
    -0.07
    645
    -0.06
    REDIENT
    -0.06
    uster
    -0.06
    ernel
    -0.06
    æķ
    -0.06
    osti
    -0.06
     Vaugh
    -0.06
    ischer
    -0.06
    POSITIVE LOGITS
     existing
    0.08
     already
    0.07
    (existing
    0.07
     initialValue
    0.07
    (edit
    0.07
    _edit
    0.07
    Ctrls
    0.06
     sẵn
    0.06
    idl
    0.06
    edit
    0.06
    Activations Density 0.010%

    No Known Activations