© 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. 128656
    Prev
    Next
    INDEX
    Explanations

    technical terms related to sensor functionality and data transmission

    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
    848
    -0.07
    uji
    -0.07
    uje
    -0.07
    938
    -0.06
     sooner
    -0.06
    erness
    -0.06
     Liberties
    -0.06
    odom
    -0.06
     наÑĤ
    -0.06
    Ðĭ
    -0.06
    POSITIVE LOGITS
    gnore
    0.08
     elim
    0.07
    afc
    0.07
    #
    0.07
    yled
    0.07
    peare
    0.07
     Modes
    0.07
     DataView
    0.06
    yle
    0.06
    .nlm
    0.06
    Activations Density 0.018%

    No Known Activations