© 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. 55711
    Prev
    Next
    INDEX
    Explanations

    phrases related to negative outcomes or poor experiences

    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
    441
    -0.08
    ees
    -0.07
    ect
    -0.07
    bers
    -0.06
    ISMATCH
    -0.06
    antar
    -0.06
    otate
    -0.06
    roll
    -0.06
    zioni
    -0.06
    aar
    -0.06
    POSITIVE LOGITS
    -case
    0.08
    ger
    0.08
    -hit
    0.07
    islav
    0.07
    amac
    0.07
    à¸Ńà¸Ķ
    0.07
    ulence
    0.07
    abi
    0.07
     ÑħÑĥд
    0.07
    ç³
    0.07
    Activations Density 0.012%

    No Known Activations