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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 4789
    Prev
    Next
    INDEX
    Explanations

    geographic locations and associated descriptions

    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
     기
    -0.06
     Ranch
    -0.06
    Ìģ
    -0.06
     ranch
    -0.06
     airports
    -0.06
    —
    -0.05
    888
    -0.05
    Interop
    -0.05
    877
    -0.05
    945
    -0.05
    POSITIVE LOGITS
     Lyme
    0.08
    ÎķÎ¥
    0.08
    slu
    0.08
    åŀĤ
    0.07
     Vict
    0.07
    acz
    0.07
     walks
    0.07
     åŀ
    0.07
     Victorian
    0.07
    anik
    0.07
    Activations Density 0.006%

    No Known Activations