© 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. 19-LLAMASCOPE-RES-32K
    11. 6036
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to project status and updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ster
    -0.15
     trag
    -0.14
    243
    -0.13
    ogan
    -0.13
    allery
    -0.13
    تÙĦ
    -0.13
     fighter
    -0.13
    )const
    -0.13
    .InnerException
    -0.12
    Caller
    -0.12
    POSITIVE LOGITS
     status
    0.27
    çĬ¶æĢģ
    0.23
     active
    0.22
     statuses
    0.22
     Status
    0.21
     ready
    0.21
     Active
    0.21
     actively
    0.20
     pending
    0.20
    ready
    0.20
    Activations Density 0.102%

    No Known Activations