© 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. 60767
    Prev
    Next
    INDEX
    Explanations

    instances of the word "finally" and phrases indicating completion or achievement

    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
    ivot
    -0.08
     continu
    -0.07
     зда
    -0.07
    amax
    -0.07
     ìĿ´ë¯¸
    -0.07
    hani
    -0.07
    continued
    -0.07
    nun
    -0.07
    елениÑı
    -0.07
     cÃłng
    -0.07
    POSITIVE LOGITS
     finally
    0.19
    finally
    0.16
     Finally
    0.15
    Finally
    0.14
    ç»Īäºİ
    0.12
    	finally
    0.10
     proper
    0.09
     truly
    0.08
     properly
    0.08
    羣æŃ£
    0.08
    Activations Density 0.040%

    No Known Activations