© 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. 16753
    Prev
    Next
    INDEX
    Explanations

    phrases related to evaluations or assessments in various 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
     eventual
    -0.08
     initially
    -0.08
     ultimately
    -0.08
     eventually
    -0.07
     ìķĦì§ģ
    -0.07
     sỼm
    -0.07
    ummies
    -0.07
    ä¸Ģ缴
    -0.07
    izm
    -0.07
    _continue
    -0.06
    POSITIVE LOGITS
     now
    0.10
    -now
    0.09
    now
    0.09
     Now
    0.08
    ished
    0.08
    Now
    0.08
     NOW
    0.08
    ìłł
    0.07
     Теп
    0.07
     artık
    0.07
    Activations Density 0.145%

    No Known Activations