© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 28764
    Prev
    Next
    INDEX
    Explanations

    phrases and terminology related to real estate services and marketing

    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
    μή
    -0.06
    ups
    -0.06
     Caption
    -0.06
    áv
    -0.06
     Gemini
    -0.06
     Summers
    -0.06
    меÑĤ
    -0.06
     Fle
    -0.06
    uns
    -0.06
    uby
    -0.06
    POSITIVE LOGITS
    stad
    0.08
    idar
    0.08
     agent
    0.07
    iset
    0.06
    REEN
    0.06
    blas
    0.06
    .agent
    0.06
    Ïĥί
    0.06
     palm
    0.06
    -agent
    0.06
    Activations Density 0.012%

    No Known Activations