© 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. 12-LLAMASCOPE-RES-32K
    11. 29876
    Prev
    Next
    INDEX
    Explanations

    terms related to diplomatic relationships and cooperation between countries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     w
    -0.17
    otec
    -0.15
    aisy
    -0.15
     wr
    -0.14
    uali
    -0.14
    _RAM
    -0.14
     part
    -0.14
     branches
    -0.14
    enburg
    -0.14
    aille
    -0.14
    POSITIVE LOGITS
    .VideoCapture
    0.15
    _lazy
    0.15
    caster
    0.15
    [rand
    0.14
    lag
    0.13
    æĺŃåĴĮ
    0.13
     Massive
    0.13
     vess
    0.13
    vore
    0.13
    untu
    0.13
    Activations Density 0.060%

    No Known Activations