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. 82863
    Prev
    Next
    INDEX
    Explanations

    programming code and syntactical elements related to SQL queries and connection handling

    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
    hood
    -0.06
    ud
    -0.06
    pha
    -0.05
    folk
    -0.05
     surprise
    -0.05
    REP
    -0.05
     cap
    -0.05
    bs
    -0.05
    /y
    -0.05
     Stevens
    -0.05
    POSITIVE LOGITS
    amarin
    0.09
    opis
    0.09
    anooga
    0.08
    ibraries
    0.08
     Baghd
    0.08
    jvu
    0.08
    .IntPtr
    0.08
    ORITY
    0.08
    eprom
    0.08
    taj
    0.08
    Activations Density 0.029%

    No Known Activations