© 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. 118479
    Prev
    Next
    INDEX
    Explanations

    code-related terms and expressions

    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
    ãĥ©ãĤ¹
    -0.08
    aticon
    -0.07
    è¢ĭ
    -0.07
    azi
    -0.07
    meden
    -0.07
     ÙĨÙĤØ´Ùĩ
    -0.07
    éĺħ读次æķ°
    -0.07
    _RCC
    -0.07
    leine
    -0.07
    reib
    -0.07
    POSITIVE LOGITS
    elt
    0.07
     Chin
    0.06
     benchmark
    0.06
    Indices
    0.06
    bench
    0.06
     Dane
    0.06
    ouve
    0.06
    erna
    0.05
    acao
    0.05
    ëĨ
    0.05
    Activations Density 0.008%

    No Known Activations