© 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. 5-LLAMASCOPE-RES-131K
    11. 125869
    Prev
    Next
    INDEX
    Explanations

    mentions of buildings or architectural structures

    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
    -0.06
    st
    -0.06
    å·±
    -0.06
    ò
    -0.06
    ster
    -0.06
     pur
    -0.06
    ibel
    -0.06
     sp
    -0.06
    aidu
    -0.06
    271
    -0.06
    POSITIVE LOGITS
    ymes
    0.07
    abay
    0.07
    ToOne
    0.07
    zac
    0.07
    ALE
    0.07
    kap
    0.07
    иÑĤом
    0.07
    _ary
    0.06
    æĬĺ
    0.06
    Dll
    0.06
    Activations Density 0.000%

    No Known Activations