© 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. 15-LLAMASCOPE-RES-131K
    11. 61569
    Prev
    Next
    INDEX
    Explanations

    references to educational programs and academic settings

    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
    ekli
    -0.07
    ripp
    -0.07
    aille
    -0.07
    icorn
    -0.06
    aeda
    -0.06
    adt
    -0.06
    ABCDEFGHIJKLMNOP
    -0.06
    /sdk
    -0.06
    abcdefghijklmnop
    -0.06
    amilia
    -0.06
    POSITIVE LOGITS
    gers
    0.07
    ufs
    0.07
    ifa
    0.06
     OnTrigger
    0.06
    ers
    0.06
     prim
    0.06
    lo
    0.06
    елен
    0.06
    ufe
    0.06
    Pod
    0.06
    Activations Density 0.028%

    No Known Activations