© 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. 93522
    Prev
    Next
    INDEX
    Explanations

    comparative phrases or terms indicating analysis and evaluation

    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
    morgan
    -0.07
    orem
    -0.07
    ÑĢоÑģÑĤ
    -0.06
    ozor
    -0.06
    γα
    -0.06
    æł¹
    -0.06
    okud
    -0.06
    ลà¸ĩ
    -0.06
    eyse
    -0.06
    ilon
    -0.06
    POSITIVE LOGITS
     other
    0.12
     others
    0.11
     anderen
    0.10
    other
    0.09
     benchmarks
    0.09
     altre
    0.08
    others
    0.08
     benchmark
    0.08
    'autres
    0.08
     known
    0.07
    Activations Density 0.035%

    No Known Activations