INDEX

Explanations

conditional phrases indicating comparisons or hypothetical situations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

Cha

-0.16

Cha

-0.16

adol

-0.15

.openConnection

-0.15

bole

-0.15

kening

-0.14

edback

-0.14

adir

-0.14

.Gen

-0.14

.djangoproject

-0.14

POSITIVE LOGITS

rowse

0.16

omm

0.14

 báºŃc

0.14

ammer

0.14

%p

0.14

 Herrera

0.13

ema

0.13

 miá»ĩng

0.13

OMATIC

0.13

eries

0.13

Activations Density 0.391%

conditional phrases indicating comparisons or hypothetical situations

No Comments

No Known Activations