INDEX

Explanations

expressions related to quantities and distributions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

acie

-0.16

ãĥªãĤ¹

-0.15

uya

-0.15

ation

-0.14

 Citizens

-0.14

ifer

-0.14

abad

-0.14

 third

-0.14

lev

-0.14

ÏįÎ½

-0.14

POSITIVE LOGITS

 altogether

0.22

 total

0.19

adin

0.18

total

0.17

alto

0.16

ofs

0.15

 jadx

0.15

 Nhá»¯ng

0.15

ylko

0.14

 Ø§ØµÙĦ

0.14

Activations Density 0.041%

expressions related to quantities and distributions

No Comments

No Known Activations