INDEX

Explanations

code-related syntax or structure elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

pper

-0.16

ntp

-0.15

elon

-0.14

Ð¸ÑĤÐ¾Ð²

-0.14

_traits

-0.14

ÑĦÑĦ

-0.14

aes

-0.14

 scales

-0.14

VID

-0.13

POSITIVE LOGITS

holm

0.17

kaar

0.16

ola

0.14

Uvs

0.14

oux

0.14

utz

0.13

 Bapt

0.13

.twig

0.13

mostat

0.13

Ø¯Ø§Ùħ

0.13

Activations Density 0.000%

code-related syntax or structure elements

No Comments

No Known Activations