© 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. 15-LLAMASCOPE-RES-131K
    6. 103762
    Prev
    Next
    INDEX
    Explanations

    phrases related to software dependencies and configurations

    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
     Mey
    -0.06
     Processes
    -0.06
     underlying
    -0.06
     premises
    -0.06
    lue
    -0.06
     Knight
    -0.05
     Ask
    -0.05
    comp
    -0.05
     Grimm
    -0.05
    ãĤ±
    -0.05
    POSITIVE LOGITS
     convention
    0.07
    è¶Ĭ
    0.07
    ãĤ¤ãĥ«
    0.07
    atoire
    0.06
    .nodeName
    0.06
    Ãło
    0.06
    нÑıÑĤ
    0.06
    Anywhere
    0.06
    etable
    0.06
     PyTuple
    0.06
    Activations Density 0.042%

    No Known Activations