© 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. 1184
    Prev
    Next
    INDEX
    Explanations

    conjunctions and phrases that link ideas or concepts

    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
    ENCIL
    -0.07
    uhn
    -0.07
    ulia
    -0.07
    ynchronously
    -0.07
    kas
    -0.07
    AXB
    -0.07
    γη
    -0.06
    olla
    -0.06
    erken
    -0.06
     âĹĦ
    -0.06
    POSITIVE LOGITS
    hardt
    0.07
    uristic
    0.06
    ä¸Ģä¸ĭ
    0.06
    nu
    0.06
    dart
    0.06
    aci
    0.06
    agg
    0.06
    çĬ¶
    0.06
    chied
    0.06
     Redemption
    0.06
    Activations Density 0.024%

    No Known Activations