© 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. 15-LLAMASCOPE-RES-131K
    11. 27207
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming, databases, and error handling

    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
    .lift
    -0.07
    roj
    -0.07
    ersed
    -0.07
    yro
    -0.07
    ispers
    -0.06
    radient
    -0.06
    CHED
    -0.06
     reciprocal
    -0.06
    ãĥ³ãĥķ
    -0.06
     sel
    -0.06
    POSITIVE LOGITS
    ñana
    0.06
     DÃŃky
    0.06
    ildo
    0.06
     âĹĦ
    0.06
    uelles
    0.06
     nick
    0.06
    antar
    0.06
    anges
    0.05
     Dynasty
    0.05
     Dyn
    0.05
    Activations Density 0.008%

    No Known Activations