INDEX

Explanations

references to governmental structures and specific regions or territories

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ienie

-0.19

 span

-0.18

Ã¡la

-0.17

 Ãĸr

-0.15

uality

-0.15

enis

-0.15

 trace

-0.15

ãĤ¦ãĤ¹

-0.14

trace

-0.14

Î»Î¿ÏĤ

-0.14

POSITIVE LOGITS

ÌĨ

0.15

Ð½Ð¾Ðº

0.14

Luo

0.14

ffi

0.14

Ä±rÄ±

0.14

igli

0.13

ulle

0.13

caffold

0.13

ainment

0.13

Activations Density 0.534%

references to governmental structures and specific regions or territories

No Comments

No Known Activations