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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 5680
    Prev
    Next
    INDEX
    Explanations

    references to purchasing illicit substances or associated terms

    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
    cio
    -0.06
     onBindViewHolder
    -0.06
    ibble
    -0.06
    reesome
    -0.06
    CREMENT
    -0.06
     banks
    -0.06
    opher
    -0.06
     Differential
    -0.06
     differentiation
    -0.06
    olis
    -0.06
    POSITIVE LOGITS
    NewProp
    0.08
    epy
    0.08
    attern
    0.07
    éf
    0.07
    edir
    0.07
    eing
    0.07
    blings
    0.07
    ायत
    0.06
    rossover
    0.06
    inges
    0.06
    Activations Density 0.000%

    No Known Activations