© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 79776
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "assembly" in various contexts

    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
    év
    -0.08
    ãĤ¦ãĤ¹
    -0.07
    aise
    -0.07
    shal
    -0.07
    że
    -0.07
    rench
    -0.07
    ải
    -0.07
    anou
    -0.06
    uml
    -0.06
     liá»ĩu
    -0.06
    POSITIVE LOGITS
    ments
    0.08
    sembl
    0.08
    sembles
    0.07
    SEMB
    0.07
    /as
    0.07
    semblies
    0.07
    bau
    0.07
    /dis
    0.07
    sembling
    0.06
    -sama
    0.06
    Activations Density 0.011%

    No Known Activations