INDEX

Explanations

terms related to claims, compensation, and legal contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

asti

-0.17

lug

-0.16

eries

-0.16

æīķ

-0.15

.biz

-0.15

reeze

-0.15

igli

-0.14

_FIFO

-0.14

ufs

-0.14

ìĿµ

-0.14

POSITIVE LOGITS

ä½Ĩ

0.17

nor

0.16

ukes

0.16

0.15

yet

0.15

 sondern

0.15

toi

0.15

 altogether

0.15

ationToken

0.14

 Ø¨ÙĦÚ©Ùĩ

0.14

Activations Density 0.113%

terms related to claims, compensation, and legal contexts

No Comments

No Known Activations