© 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. 93795
    Prev
    Next
    INDEX
    Explanations

    instances of the word "massive" or related to significant size or impact

    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
    se
    -0.07
    ÑĢеж
    -0.06
    ken
    -0.06
    ein
    -0.06
    bie
    -0.06
    ropa
    -0.06
    soever
    -0.06
    467
    -0.06
    phans
    -0.06
    ighth
    -0.06
    POSITIVE LOGITS
     amounts
    0.13
    -scale
    0.12
    amount
    0.12
     amount
    0.11
     Amount
    0.10
    Amount
    0.09
    cly
    0.09
     strides
    0.08
    agrid
    0.08
    Domains
    0.08
    Activations Density 0.019%

    No Known Activations