INDEX

Explanations

names of individuals, particularly those associated with significant roles or accomplishments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

hear

-0.16

-0.15

iff

-0.14

inch

-0.14

erez

-0.14

 upfront

-0.14

oper

-0.14

pin

-0.13

swe

-0.13

POSITIVE LOGITS

OUNDS

0.15

æ²»

0.14

 Lease

0.14

ç¥Ŀ

0.14

ioxide

0.14

acha

0.14

 ÙĩÙħÛĮÙĨ

0.14

 Turk

0.14

 Econom

0.14

Îŀ

0.14

Activations Density 0.421%

names of individuals, particularly those associated with significant roles or accomplishments

No Comments

No Known Activations