© 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. 30-LLAMASCOPE-RES-32K
    11. 23147
    Prev
    Next
    INDEX
    Explanations

    terms related to components in a programming or software context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ispers
    -0.17
    phia
    -0.17
    lbrace
    -0.15
     Ñĥгод
    -0.15
    GMEM
    -0.15
    InitStruct
    -0.14
    'gc
    -0.14
    itti
    -0.14
    _QMARK
    -0.14
    ucher
    -0.14
    POSITIVE LOGITS
     component
    1.23
     Component
    1.10
    component
    1.09
     components
    1.05
    Component
    1.02
    -component
    0.99
    _component
    0.98
     COMPONENT
    0.95
     Components
    0.94
     componente
    0.91
    Activations Density 0.167%

    No Known Activations