Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 25-LLAMASCOPE-RES-32K
    6. 22769
    Prev
    Next
    INDEX
    Explanations

    concepts related to algorithms and network structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    plots
    -0.14
    chl
    -0.14
    esis
    -0.13
     ëĦ¤ìĿ´íĬ¸
    -0.13
    _serialize
    -0.13
    ignum
    -0.13
    aise
    -0.13
    /vnd
    -0.13
    _simulation
    -0.13
    enge
    -0.13
    POSITIVE LOGITS
     training
    0.22
     feeding
    0.20
     learn
    0.19
     learns
    0.19
    learn
    0.19
     learning
    0.18
     fed
    0.18
     trained
    0.18
     learned
    0.17
    Learn
    0.17
    Activations Density 0.028%

    No Known Activations