© 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. 5-LLAMASCOPE-RES-32K
    6. 15712
    Prev
    Next
    INDEX
    Explanations

    the word "despite" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    opher
    -0.17
    ye
    -0.16
    ãĥ¼ãĥľ
    -0.14
    afia
    -0.14
    égorie
    -0.14
    شتÙĩ
    -0.14
     تÙĩ
    -0.14
    .mybatisplus
    -0.14
    scope
    -0.13
    Ńå·ŀ
    -0.13
    POSITIVE LOGITS
    ırak
    0.17
    estro
    0.15
    cul
    0.15
     accounting
    0.15
     Thing
    0.15
     Companion
    0.15
    csr
    0.14
     upt
    0.14
    adas
    0.14
    iras
    0.14
    Activations Density 0.039%

    No Known Activations