© 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. 77568
    Prev
    Next
    INDEX
    Explanations

    references to space and rocket launches

    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
     sieve
    -0.06
    .null
    -0.06
    Äįi
    -0.05
    bish
    -0.05
    .rmi
    -0.05
     ple
    -0.05
    ild
    -0.05
     fos
    -0.05
     REC
    -0.05
    arrant
    -0.05
    POSITIVE LOGITS
     mission
    0.09
     missions
    0.09
    mission
    0.08
    Mission
    0.08
     launch
    0.08
    missions
    0.08
    .launch
    0.07
    æħİ
    0.07
     è©
    0.07
     Mission
    0.07
    Activations Density 0.007%

    No Known Activations