© 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. 54784
    Prev
    Next
    INDEX
    Explanations

    words related to complementary or supporting elements

    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
    beiter
    -0.07
    nees
    -0.07
    ilities
    -0.07
    inals
    -0.07
    emas
    -0.06
    liest
    -0.06
    ed
    -0.06
    _usec
    -0.06
    keeping
    -0.06
    zin
    -0.06
    POSITIVE LOGITS
    tester
    0.07
     éĺ
    0.07
    ust
    0.07
    .comp
    0.07
    ÑĶÑĹ
    0.07
    vier
    0.06
    orado
    0.06
    ador
    0.06
    missions
    0.06
    aign
    0.06
    Activations Density 0.008%

    No Known Activations