© 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. 40745
    Prev
    Next
    INDEX
    Explanations

    references to specific movie titles and their associated popular culture

    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
    å·§
    -0.08
    uye
    -0.07
    ORY
    -0.07
    egan
    -0.07
    #echo
    -0.07
    .Accessible
    -0.07
    gang
    -0.06
    ãĥIJãĤ¤
    -0.06
    apsed
    -0.06
    Ñĥг
    -0.06
    POSITIVE LOGITS
    bst
    0.07
    flight
    0.06
    811
    0.06
    365
    0.06
     Lester
    0.06
    etti
    0.06
    791
    0.06
     creatures
    0.06
     warm
    0.06
     flight
    0.06
    Activations Density 0.002%

    No Known Activations