INDEX

Explanations

symbols and syntax related to programming or coding structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 Rodgers

-0.14

orer

-0.14

 Rowe

-0.13

 Rainbow

-0.13

(reordered

-0.13

Ø±ÙĪØ²

-0.12

kaar

-0.12

 Robertson

-0.12

okino

-0.12

asley

-0.12

POSITIVE LOGITS

1.55

1.19

)r

0.86

.r

0.85

=r

0.80

(r

0.79

 ÑĢ

0.79

:r

0.78

0.77

$r

0.75

Activations Density 0.156%

symbols and syntax related to programming or coding structures

No Comments

No Known Activations