© 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. 24-LLAMASCOPE-RES-32K
    11. 7692
    Prev
    Next
    INDEX
    Explanations

    complex emotional or social themes within narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    isle
    -0.16
     ait
    -0.15
     Äij
    -0.14
    unker
    -0.14
     ControllerBase
    -0.14
    ä¹ħä¹ħ
    -0.14
     lle
    -0.14
    -Sah
    -0.13
    aders
    -0.13
    taire
    -0.13
    POSITIVE LOGITS
     Ellison
    0.17
    èģ¯
    0.15
     Kee
    0.14
    거리
    0.14
    -than
    0.14
     nons
    0.14
     latter
    0.14
    ellation
    0.13
     Prest
    0.13
     Vie
    0.13
    Activations Density 0.229%

    No Known Activations