© 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. 15-LLAMASCOPE-RES-32K
    11. 5737
    Prev
    Next
    INDEX
    Explanations

    mentions of significant events or institutions related to international relations and diplomacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    âĢ¦but
    -0.22
    âĢ¦↵↵↵
    -0.21
    âĢ¦and
    -0.21
    âĢ¦it
    -0.19
    âĢ¦↵
    -0.19
    âĢ¦I
    -0.19
    âĢ¦the
    -0.18
    âĢ¦↵↵
    -0.17
     [âĢ¦]↵
    -0.17
     âĢ¦↵
    -0.16
    POSITIVE LOGITS
     @}
    0.13
    plements
    0.12
    é§ħå¾ĴæŃ©
    0.12
     the
    0.12
    qml
    0.12
    orough
    0.11
     ActionTypes
    0.11
    .Îł
    0.11
    AdminController
    0.11
    ););↵
    0.11
    Activations Density 16.975%

    No Known Activations