Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 4336
    Prev
    Next
    INDEX
    Explanations

    references to past roles or occupations of individuals

    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
    former
    -0.09
     Former
    -0.09
    Former
    -0.09
    âĢĮاÙĨ
    -0.08
     former
    -0.08
    /he
    -0.08
    ãĥ¼ãĥį
    -0.07
    缮åīį
    -0.07
     formerly
    -0.07
     zatÃŃm
    -0.07
    POSITIVE LOGITS
    /current
    0.14
    ly
    0.09
    /new
    0.08
    most
    0.08
     longtime
    0.07
    -president
    0.07
     president
    0.07
    -generation
    0.07
    ãĢħ
    0.07
    ely
    0.07
    Activations Density 0.016%

    No Known Activations