INDEX

Explanations

affirmations and confirmations in discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

ÑĳÑĢ

-0.15

ersiz

-0.15

ëĦ·

-0.14

 Proxy

-0.14

/tiny

-0.14

acter

-0.14

od

-0.13

 pÅ¯

-0.13

Ð°Ð½Ð¸ÑĨ

-0.13

ensis

-0.13

POSITIVE LOGITS

ãĥ³ãĥ

0.16

ÅĤad

0.14

eward

0.14

onde

0.14

wend

0.14

uma

0.14

deaux

0.14

 Ende

0.14

etto

0.14

Activations Density 0.111%

affirmations and confirmations in discussions

No Comments

No Known Activations