© 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. 2-LLAMASCOPE-RES-32K
    11. 28057
    Prev
    Next
    INDEX
    Explanations

    phrases related to tuning in or watching something, particularly television or events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    osy
    -0.15
    ervals
    -0.14
    ipple
    -0.14
    osal
    -0.14
     pul
    -0.14
    sta
    -0.14
    ioned
    -0.14
     conse
    -0.14
    ½
    -0.14
     Sokol
    -0.13
    POSITIVE LOGITS
    736
    0.17
    assi
    0.17
    ezi
    0.16
    ãĤ¤ãĥ¤
    0.15
    Drv
    0.15
    elib
    0.14
    ALES
    0.14
    Ī
    0.14
    Interop
    0.14
    locator
    0.14
    Activations Density 0.011%

    No Known Activations