© 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. 22-LLAMASCOPE-RES-131K
    11. 3700
    Prev
    Next
    INDEX
    Explanations

    references to technology and gadgets

    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
    uild
    -0.07
    bane
    -0.07
     commitments
    -0.06
    iland
    -0.06
    commit
    -0.06
    cem
    -0.06
    IEW
    -0.06
    ongan
    -0.06
    ä½ľ
    -0.06
     Commit
    -0.06
    POSITIVE LOGITS
     Charge
    0.13
     charge
    0.12
     charging
    0.11
    Charge
    0.10
     charged
    0.10
     power
    0.10
    åħħ
    0.10
     Charging
    0.10
     Charges
    0.10
     charges
    0.09
    Activations Density 0.003%

    No Known Activations