INDEX

Explanations

contextual references to significant actions or events in a narrative

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

à¸¢à¸ĩ

-0.15

bstract

-0.13

Ã©al

-0.13

Ð²Ð¸ÑĩÐ°Ð¹

-0.12

auge

-0.12

ìĥĿëĭĺ

-0.12

quence

-0.12

ÑģÑĥÑĤÑģÑĤÐ²

-0.11

ìĿ´ìħĺ

-0.11

 getClass

-0.11

POSITIVE LOGITS

 that

0.88

 THAT

0.85

 That

0.81

That

0.77

that

0.74

éĤ£

0.70

éĤ£ä¸ª

0.69

	that

0.67

 those

0.66

_that

0.66

Activations Density 2.486%

contextual references to significant actions or events in a narrative

No Comments

No Known Activations