INDEX

Explanations

expressions related to value assessment and comparison

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

ieu

-0.16

ÙĬÙĨØ§

-0.15

undles

-0.15

tie

-0.15

.sharedInstance

-0.14

slaught

-0.14

ijk

-0.14

vyk

-0.14

ours

-0.14

rod

-0.14

POSITIVE LOGITS

 whom

0.15

 Polar

0.14

oned

0.14

à¹īà¸²à¸¢

0.14

agem

0.13

sen

0.13

ç·¨

0.13

ilater

0.13

olicited

0.13

ioned

0.13

Activations Density 0.364%

expressions related to value assessment and comparison

No Comments

No Known Activations