© 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 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. 71214
    Prev
    Next
    INDEX
    Explanations

    components and processes related to audio and signal processing equipment

    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
    isl
    -0.07
    wich
    -0.06
    (para
    -0.06
    638
    -0.06
    öm
    -0.06
    544
    -0.06
    ERR
    -0.06
    ãĤ¹ãĥ¬
    -0.06
    TX
    -0.06
    irie
    -0.06
    POSITIVE LOGITS
    obo
    0.07
    esser
    0.07
    ượ
    0.07
    ymoon
    0.07
    nj
    0.07
    ADS
    0.07
    iculo
    0.07
    figures
    0.07
    ikes
    0.06
    åºĬ
    0.06
    Activations Density 0.058%

    No Known Activations