© 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. 5-LLAMASCOPE-RES-131K
    11. 125957
    Prev
    Next
    INDEX
    Explanations

    numeric data or statistics presented in a document

    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
    rove
    -0.06
    NES
    -0.06
     Bru
    -0.06
    пе
    -0.05
     "
    -0.05
    \modules
    -0.05
    OLUTE
    -0.05
    erval
    -0.05
    _paper
    -0.05
    aan
    -0.05
    POSITIVE LOGITS
     geil
    0.07
    agogue
    0.07
     kvin
    0.07
    licken
    0.07
    beeld
    0.07
    (#)
    0.07
    dojo
    0.06
    venta
    0.06
     egt
    0.06
    zzle
    0.06
    Activations Density 0.009%

    No Known Activations