INDEX

Explanations

elements related to instructions or manuals

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

orraine

-0.15

adiens

-0.15

.Apis

-0.14

Ï

-0.14

asta

-0.14

USB

-0.14

.getCmp

-0.14

heits

-0.13

ifornia

-0.13

Ø§Øµ

-0.13

POSITIVE LOGITS

 foss

0.15

eliness

0.14

thood

0.14

ises

0.14

 Ø´Ø¯ÙĨ

0.14

aises

0.13

onas

0.13

prenom

0.13

iform

0.13

 Î±Î½ÏĦÎ¹

0.13

Activations Density 0.021%

elements related to instructions or manuals

No Comments

No Known Activations

elements related to instructions or manuals

No Comments

No Known Activations