© 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. 6126
    Prev
    Next
    INDEX
    Explanations

    terms related to radar technology and its performance characteristics

    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
    ìĿ´ìŀIJ
    -0.14
     prostitut
    -0.14
    sto
    -0.13
    они
    -0.13
     accessory
    -0.13
    \Php
    -0.13
    коз
    -0.12
    urch
    -0.12
     klu
    -0.12
     xxx
    -0.12
    POSITIVE LOGITS
     ones
    0.35
    -only
    0.26
     version
    0.24
     counterparts
    0.22
     mode
    0.21
     stuff
    0.21
     Ones
    0.21
     counterpart
    0.21
     versions
    0.20
    çīĪæľ¬
    0.20
    Activations Density 0.819%

    No Known Activations