© 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. 20-LLAMASCOPE-RES-32K
    11. 13009
    Prev
    Next
    INDEX
    Explanations

    terms related to dietary habits and weight loss strategies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OffsetTable
    -0.21
    GenerationStrategy
    -0.18
    erdem
    -0.16
    UrlParser
    -0.16
    InitStruct
    -0.16
     пÑĢоÑĦеÑģÑģионалÑĮ
    -0.16
    GuidId
    -0.15
    CppType
    -0.15
    pNet
    -0.15
     ÑĦÑĥнда
    -0.15
    POSITIVE LOGITS
    ï¼Į以åıĬ
    0.14
    .getSeconds
    0.14
    èĬĻ
    0.12
     inertia
    0.12
    âĢ¦↵
    0.12
    <|end_of_text|>
    0.11
     beta
    0.11
    âĢ¦)
    0.11
    uffy
    0.11
    é§
    0.11
    Activations Density 2.601%

    No Known Activations