© 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. 118619
    Prev
    Next
    INDEX
    Explanations

    concepts related to decline or deterioration

    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
     Laden
    -0.06
    ç¿°
    -0.06
    ãĤ¹ãĤ¿ãĥ¼
    -0.06
    orks
    -0.06
    oda
    -0.06
    existent
    -0.06
    erie
    -0.06
    tuÄŁ
    -0.06
    ahn
    -0.05
    akeup
    -0.05
    POSITIVE LOGITS
     toward
    0.10
     towards
    0.10
     Towards
    0.09
    Towards
    0.09
     slide
    0.08
    slide
    0.07
     Into
    0.07
     headed
    0.07
     Slide
    0.07
    Into
    0.07
    Activations Density 0.029%

    No Known Activations