Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 56203
    Prev
    Next
    INDEX
    Explanations

    sections of code related to comments and documentation

    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
    osomes
    -0.07
    anitize
    -0.07
    rijk
    -0.07
    ÑĩÑĥк
    -0.07
    803
    -0.07
    _locals
    -0.07
    ÑĢол
    -0.07
    िवस
    -0.07
    olis
    -0.07
    arters
    -0.07
    POSITIVE LOGITS
     Legend
    0.06
    Lane
    0.06
    atform
    0.06
    anes
    0.05
     open
    0.05
     '\''
    0.05
    orden
    0.05
    dre
    0.05
    abinet
    0.05
    atch
    0.05
    Activations Density 0.005%

    No Known Activations