© 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. 14-LLAMASCOPE-RES-32K
    11. 27792
    Prev
    Next
    INDEX
    Explanations

    names and titles of persons involved in government or diplomatic roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k
    Configuration
    fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    Features
    32,768
    Data Type
    bfloat16
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    201
    -0.18
    200
    -0.17
    Û²Û°Û±
    -0.17
     recent
    -0.16
     Victorian
    -0.16
     Bush
    -0.15
     Evo
    -0.15
    191
    -0.15
     Dro
    -0.15
     ìµľê·¼
    -0.15
    POSITIVE LOGITS
    196
    0.42
    197
    0.41
    ï¼ĪæĺŃåĴĮ
    0.34
     USSR
    0.32
    195
    0.30
     Soviet
    0.29
    198
    0.26
     Soviets
    0.23
    Û±Û¹Û¶
    0.23
     Ð¡Ð¡Ð¡Ðł
    0.22
    Activations Density 1.690%

    No Known Activations