© 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. 60853
    Prev
    Next
    INDEX
    Explanations

    phrases related to storytelling structure and progression

    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
    ettel
    -0.07
    keit
    -0.07
    lob
    -0.07
    ủi
    -0.07
    enze
    -0.06
    .esp
    -0.06
    ÙĪاع
    -0.06
    tel
    -0.06
    еÑģÑĤва
    -0.06
    ond
    -0.06
    POSITIVE LOGITS
     till
    0.07
     til
    0.06
     outset
    0.06
     inception
    0.06
    INARY
    0.06
     standpoint
    0.06
     jusqu
    0.06
    uzzer
    0.06
     until
    0.06
    /original
    0.05
    Activations Density 0.006%

    No Known Activations