INDEX

Explanations

information related to online research and accessibility

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 removeFrom

-0.15

Ð¾ÐºÑĢÐµÐ¼

-0.15

egin

-0.15

 nackte

-0.15

 ëıĮ

-0.15

æ¢¨

-0.15

lier

-0.14

eparator

-0.14

 Vaults

-0.14

 aest

-0.13

POSITIVE LOGITS

bay

0.17

bay

0.17

lum

0.17

bau

0.16

eus

0.16

_CLIP

0.16

Lum

0.15

ÑĪÐ¸Ð²

0.15

0.14

Å¡ek

0.14

Activations Density 0.045%

information related to online research and accessibility

No Comments

No Known Activations