Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 128791
    Prev
    Next
    INDEX
    Explanations

    instances of prepositions indicating location or origin

    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
    ebra
    -0.08
    amburg
    -0.07
    createView
    -0.07
    raquo
    -0.06
    adas
    -0.06
    acier
    -0.06
    eldon
    -0.06
    íķĻëħĦëıĦ
    -0.06
    ette
    -0.06
    iez
    -0.06
    POSITIVE LOGITS
    é¦Ļ
    0.07
    abo
    0.07
    ëĬIJ
    0.06
    ABI
    0.06
    avit
    0.06
    ÄĽtÅ¡
    0.06
     dich
    0.06
    agn
    0.06
    cle
    0.06
    ANN
    0.06
    Activations Density 0.001%

    No Known Activations