© 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. 40618
    Prev
    Next
    INDEX
    Explanations

    references to experiences and connections to past events or histories within a camp context

    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
     leisure
    -0.06
    rouch
    -0.06
     office
    -0.06
    ottes
    -0.06
     monthly
    -0.06
    ÑĢоÑĩ
    -0.06
     wedge
    -0.06
    ips
    -0.05
    Routine
    -0.05
    .native
    -0.05
    POSITIVE LOGITS
     camps
    0.11
     summer
    0.10
     camp
    0.10
     Camp
    0.10
    summer
    0.09
     Summer
    0.08
    å¤ı
    0.08
     å¤ı
    0.08
     summers
    0.07
     participants
    0.07
    Activations Density 0.295%

    No Known Activations