© 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. 3-LLAMASCOPE-RES-32K
    11. 16797
    Prev
    Next
    INDEX
    Explanations

    references to treaties and agreements, particularly those related to peace and international relations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onto
    -0.19
    799
    -0.15
    acre
    -0.15
    n
    -0.14
    OURNAL
    -0.14
    796
    -0.14
     ceased
    -0.14
    ÑĥÑĪ
    -0.14
     bes
    -0.14
    èį·
    -0.14
    POSITIVE LOGITS
    eturn
    0.16
    iger
    0.15
    sson
    0.15
    ichick
    0.15
    laÅŁ
    0.14
    etz
    0.14
    ichel
    0.14
    ovÃŃ
    0.14
    rage
    0.14
    son
    0.14
    Activations Density 0.009%

    No Known Activations