© 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. 28766
    Prev
    Next
    INDEX
    Explanations

    conditional statements and expressions of willingness or preference

    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
    emente
    -0.07
    iete
    -0.07
    ffen
    -0.07
    dete
    -0.07
     unless
    -0.06
    Úĺ
    -0.06
    λον
    -0.06
    ừa
    -0.06
    ój
    -0.06
     vừa
    -0.06
    POSITIVE LOGITS
     yes
    0.12
    yes
    0.10
     maybe
    0.10
     yeah
    0.09
     Yes
    0.09
     might
    0.09
    Yes
    0.09
     YES
    0.09
     THEN
    0.08
    maybe
    0.08
    Activations Density 0.022%

    No Known Activations