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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 15995
    Prev
    Next
    INDEX
    Explanations

    references to the name "Lamb" or variations of it

    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
    iske
    -0.08
    عاÙħ
    -0.08
    ober
    -0.07
    RowAt
    -0.07
    lea
    -0.07
    yen
    -0.07
    ract
    -0.07
    ëªħ
    -0.07
    iffies
    -0.07
    arpa
    -0.06
    POSITIVE LOGITS
    son
    0.08
    ellar
    0.08
    orghini
    0.08
    umba
    0.07
    den
    0.07
    ur
    0.07
    ishly
    0.07
     Giul
    0.07
    grave
    0.07
    ton
    0.07
    Activations Density 0.010%

    No Known Activations