© 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. 8-LLAMASCOPE-RES-32K
    11. 30534
    Prev
    Next
    INDEX
    Explanations

    discussions about problems in media adaptations and their impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 8-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awai
    -0.16
    ANE
    -0.16
    ane
    -0.15
    esis
    -0.15
    ritz
    -0.15
    foy
    -0.14
     suspended
    -0.14
    ctor
    -0.14
     grav
    -0.14
     svens
    -0.14
    POSITIVE LOGITS
     vX
    0.16
     Vig
    0.14
    /platform
    0.14
    walker
    0.13
    wed
    0.13
    mini
    0.13
    setQuery
    0.13
     Substance
    0.13
    <quote
    0.13
    ousand
    0.13
    Activations Density 0.409%

    No Known Activations