© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 74710
    Prev
    Next
    INDEX
    Explanations

    technical terminology and concepts related to semiconductor physics or electrical engineering

    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
    enco
    -0.08
    linkplain
    -0.07
    #
    -0.07
    _Lean
    -0.07
    hlen
    -0.07
    essel
    -0.06
    ogue
    -0.06
    å§IJ
    -0.06
     onDataChange
    -0.06
    _IOC
    -0.06
    POSITIVE LOGITS
     Wells
    0.07
    Comparator
    0.06
    ãĤ±ãĥĥãĥĪ
    0.06
     Messaging
    0.06
     charging
    0.06
     Charging
    0.06
     Raz
    0.06
     Mobility
    0.06
     drain
    0.06
     Fowler
    0.06
    Activations Density 0.017%

    No Known Activations