© 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. 119625
    Prev
    Next
    INDEX
    Explanations

    elements related to organizational growth and relocation

    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
     Tone
    -0.07
    olar
    -0.07
     rek
    -0.06
     networks
    -0.06
     Hud
    -0.06
     arms
    -0.06
    arges
    -0.06
     оÑĤп
    -0.06
     Hospitals
    -0.06
    arms
    -0.05
    POSITIVE LOGITS
     move
    0.15
     moved
    0.14
    move
    0.14
    -move
    0.13
     Move
    0.13
    Move
    0.13
    æIJ¬
    0.13
     MOVE
    0.12
    moved
    0.12
     moving
    0.12
    Activations Density 0.187%

    No Known Activations