INDEX

Explanations

descriptive phrases outlining objectives or purposes in text

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

edd

-0.16

zin

-0.15

ushing

-0.15

ead

-0.15

-0.14

enos

-0.14

åĥıæĺ¯

-0.14

ab

-0.14

tha

-0.14

TA

-0.13

POSITIVE LOGITS

to

0.25

 ÑĩÑĤÐ¾Ð±Ñĭ

0.20

tw

0.18

 ÑīÐ¾Ð±

0.17

 Î½Î±

0.16

Tw

0.16

to

0.16

omin

0.15

ieber

0.15

ToShow

0.15

Activations Density 0.049%

descriptive phrases outlining objectives or purposes in text

No Comments

No Known Activations