© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 9-LLAMASCOPE-RES-32K
    6. 6513
    Prev
    Next
    INDEX
    Explanations

    technical terms and complex structure related to organizations or integration in a system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    INARY
    -0.15
    frau
    -0.15
    aku
    -0.14
    erset
    -0.14
    allas
    -0.14
    arters
    -0.14
    arten
    -0.13
    assic
    -0.13
     LIABILITY
    -0.13
    dre
    -0.13
    POSITIVE LOGITS
    utton
    0.17
    uns
    0.15
    ort
    0.15
    ades
    0.15
    ForObject
    0.15
    shade
    0.15
     pace
    0.14
    ellation
    0.14
    TreeWidgetItem
    0.14
     Vend
    0.14
    Activations Density 0.505%

    No Known Activations