INDEX

Explanations

programming-related function definitions and return statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

 null

-0.26

null

-0.21

-null

-0.16

uracy

-0.16

=true

-0.15

ãĥ¥

-0.15

typeof

-0.15

(null

-0.14

	null

-0.14

/null

-0.14

POSITIVE LOGITS

 None

0.78

None

0.71

(None

0.57

	None

0.50

 none

0.48

_None

0.47

 True

0.47

 False

0.46

,None

0.46

 NONE

0.43

Activations Density 0.027%

programming-related function definitions and return statements

No Comments

No Known Activations