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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 61181
    Prev
    Next
    INDEX
    Explanations

    quantities and numerical data related to various entities or categories

    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
    одаÑĢ
    -0.07
    orum
    -0.06
    infra
    -0.06
    oÄŁ
    -0.06
     doorstep
    -0.06
    ами
    -0.06
     reve
    -0.06
    STITUTE
    -0.06
     Colony
    -0.06
    uger
    -0.06
    POSITIVE LOGITS
     major
    0.07
    olis
    0.06
     distinct
    0.06
     rivers
    0.06
    .cam
    0.06
     feeder
    0.06
    unas
    0.06
    _ISO
    0.06
     publicly
    0.06
     town
    0.06
    Activations Density 0.027%

    No Known Activations