© 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. 18-LLAMASCOPE-RES-32K
    11. 6477
    Prev
    Next
    INDEX
    Explanations

    dialogues and interactions between characters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    radient
    -0.15
    оÑĢÑĤ
    -0.15
    crest
    -0.14
    ãĤ´ãĥª
    -0.13
     Lah
    -0.13
     ëĤĺëĿ¼
    -0.13
     @}
    -0.13
    avi
    -0.13
    onga
    -0.13
    .reflect
    -0.12
    POSITIVE LOGITS
     pointing
    0.39
    æĮĩ
    0.37
     pointed
    0.34
     pointers
    0.32
     point
    0.31
     pointer
    0.31
     Point
    0.31
    -point
    0.28
     POINT
    0.28
    point
    0.27
    Activations Density 0.182%

    No Known Activations