© 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. 21-LLAMASCOPE-RES-32K
    6. 15774
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or events related to historical or political contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Reconstruction
    -0.17
    abelle
    -0.16
    iland
    -0.15
    orado
    -0.14
    asal
    -0.14
    actionDate
    -0.14
    sworth
    -0.14
    mé
    -0.14
    راÙģ
    -0.14
    ذÛĮر
    -0.14
    POSITIVE LOGITS
     Cold
    0.36
     Soviet
    0.34
     East
    0.30
    Cold
    0.29
     Eastern
    0.27
     Soviets
    0.26
     communism
    0.25
     communist
    0.24
    East
    0.24
     cold
    0.24
    Activations Density 0.120%

    No Known Activations