© 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. 126049
    Prev
    Next
    INDEX
    Explanations

    instances of personal growth and reflections on 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
    anny
    -0.07
    essler
    -0.06
    ENTA
    -0.06
    gın
    -0.06
    wor
    -0.06
    esting
    -0.06
    .kotlin
    -0.06
    iani
    -0.06
     Podesta
    -0.06
    è¿İ
    -0.05
    POSITIVE LOGITS
    rost
    0.08
     hour
    0.08
     داش
    0.07
    éĻ©
    0.07
    Wunused
    0.07
     yesterday
    0.07
    lfw
    0.07
    æĪijçļĦ
    0.06
    ibu
    0.06
    _ISO
    0.06
    Activations Density 0.025%

    No Known Activations