INDEX

Explanations

phrases indicating distances or locations in relation to other places

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

Bond

-0.14

Ð²Ð°Ð½

-0.14

ãĤ±ãĥ¼ãĤ¹

-0.14

AINED

-0.14

ustr

-0.14

 bonded

-0.13

 nedir

-0.13

itti

-0.13

eros

-0.13

tro

-0.13

POSITIVE LOGITS

monds

0.17

enci

0.17

 stiff

0.15

words

0.15

ERIC

0.15

.pp

0.15

erville

0.14

stab

0.14

ãĥ«ãĥķ

0.14

abis

0.14

Activations Density 0.018%

phrases indicating distances or locations in relation to other places

No Comments

No Known Activations