© 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. 126281
    Prev
    Next
    INDEX
    Explanations

    significant achievements or turning points 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
     nÃło
    -0.07
    gons
    -0.06
    olum
    -0.06
    usz
    -0.06
    bak
    -0.06
     overrun
    -0.05
    bÃŃr
    -0.05
    abei
    -0.05
    eson
    -0.05
    bian
    -0.05
    POSITIVE LOGITS
     for
    0.08
     considering
    0.07
    ference
    0.07
    ãĤĮ
    0.07
    umbing
    0.07
     бед
    0.07
     regarding
    0.06
    unci
    0.06
    ?url
    0.06
     nejen
    0.06
    Activations Density 0.017%

    No Known Activations