© 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. 62046
    Prev
    Next
    INDEX
    Explanations

    mentions of character names or references to literary figures

    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
    ymm
    -0.08
    bru
    -0.08
    istra
    -0.07
     salopes
    -0.07
    iska
    -0.07
    afia
    -0.07
    [*
    -0.07
    ãĢĤä»Ĭ
    -0.07
    ervo
    -0.07
    isku
    -0.07
    POSITIVE LOGITS
    еÑī
    0.07
    ault
    0.06
     cons
    0.06
     speech
    0.06
     mbox
    0.06
    åīĽ
    0.06
     Embedded
    0.06
     McGr
    0.06
    ãĥ¼ãĤ¹ãĥĪ
    0.06
     Socket
    0.06
    Activations Density 0.002%

    No Known Activations