© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 40721
    Prev
    Next
    INDEX
    Explanations

    phrases related to decisions and reactions in organizational contexts

    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
    odon
    -0.06
     respectively
    -0.06
    odont
    -0.06
     organisations
    -0.06
    illion
    -0.06
    aked
    -0.06
     personally
    -0.06
    ãĤ¥
    -0.06
    pect
    -0.05
     Becker
    -0.05
    POSITIVE LOGITS
     itself
    0.21
     its
    0.19
     Its
    0.16
    Its
    0.15
    its
    0.13
    åħ¶
    0.11
    ï¼Įå®ĥ
    0.09
    åıĬåħ¶
    0.09
    å®ĥ
    0.09
     jejÃŃm
    0.09
    Activations Density 0.305%

    No Known Activations