INDEX

Explanations

questions about problem-solving and seeking solutions or advice

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

iju

-0.17

astr

-0.17

unge

-0.15

RESSED

-0.15

fant

-0.15

unate

-0.14

erd

-0.14

»

-0.14

ft

-0.14

rupa

-0.13

POSITIVE LOGITS

.pointer

0.14

åģ¥

0.14

zag

0.14

celik

0.14

uala

0.14

 Cros

0.14

igli

0.14

_pointer

0.14

autoreleasepool

0.14

skb

0.14

Activations Density 0.081%

questions about problem-solving and seeking solutions or advice

No Comments

No Known Activations