© 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. 87248
    Prev
    Next
    INDEX
    Explanations

    descriptions of scenic or attractive views

    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
    roy
    -0.08
    pta
    -0.07
    ROY
    -0.07
     Mate
    -0.07
    ça
    -0.06
    fly
    -0.06
    ober
    -0.06
    aney
    -0.06
    nea
    -0.06
    rani
    -0.06
    POSITIVE LOGITS
    ag
    0.07
    swire
    0.06
    enz
    0.06
    ionic
    0.06
     across
    0.06
    rett
    0.06
    mund
    0.06
    eus
    0.06
    istical
    0.06
    RunWith
    0.05
    Activations Density 0.006%

    No Known Activations