© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 5466
    Prev
    Next
    INDEX
    Explanations

    phrases indicating critique or negative outcomes of a situation

    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
     trom
    -0.07
    udden
    -0.07
    å¶
    -0.07
    ëįĺ
    -0.07
    zer
    -0.06
     ìŀĪëĭ¤ê³ł
    -0.06
    IfExists
    -0.06
    _Width
    -0.06
     آذ
    -0.06
    noop
    -0.06
    POSITIVE LOGITS
     eventual
    0.12
     eventually
    0.11
     subsequent
    0.11
     later
    0.10
     Eventually
    0.09
     subsequently
    0.09
    Eventually
    0.09
     ultimately
    0.08
     outcome
    0.08
    later
    0.08
    Activations Density 0.060%

    No Known Activations