© 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. 15-LLAMASCOPE-RES-131K
    6. 90116
    Prev
    Next
    INDEX
    Explanations

    references to companies and their interactions in a business context

    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
    BCM
    -0.06
    CLU
    -0.06
     redundant
    -0.06
     wind
    -0.06
    WEEN
    -0.06
    abel
    -0.05
    ITED
    -0.05
    894
    -0.05
     beyond
    -0.05
    undan
    -0.05
    POSITIVE LOGITS
    GtkWidget
    0.07
     Ø´Ú©
    0.07
    ôm
    0.07
    ProcAddress
    0.07
    rypted
    0.07
    /******/
    0.07
    ÃŁen
    0.07
    åĩºçīĪ
    0.07
    obble
    0.06
    vette
    0.06
    Activations Density 0.039%

    No Known Activations