© 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. 87251
    Prev
    Next
    INDEX
    Explanations

    references to the concept of 'it' in various contexts throughout the document

    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
    IGHLIGHT
    -0.07
    ìĦľëĬĶ
    -0.07
    plusplus
    -0.07
     æĻ®
    -0.07
    ziel
    -0.07
    .GetObject
    -0.07
    Https
    -0.07
    heten
    -0.07
    herent
    -0.06
    icerca
    -0.06
    POSITIVE LOGITS
    iner
    0.08
    ra
    0.07
    ington
    0.06
    atto
    0.06
    ener
    0.06
    88
    0.06
    ic
    0.06
    ography
    0.06
    82
    0.06
    ante
    0.06
    Activations Density 0.008%

    No Known Activations