INDEX

Explanations

statements of uncertainty or hesitation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ä»¥ä¸Ĭ

-0.14

ea

-0.14

umbn

-0.14

 finally

-0.13

å½±

-0.13

tas

-0.13

 Lastly

-0.13

hi

-0.13

olid

-0.13

venta

-0.13

POSITIVE LOGITS

ensburg

0.17

yles

0.16

READ

0.15

 Ð¢Ð°Ð¼

0.15

ADVERTISEMENT

0.15

 áº¥y

0.14

ium

0.14

FILE

0.13

<<-

0.13

SEE

0.13

Activations Density 0.025%

statements of uncertainty or hesitation

No Comments

No Known Activations