INDEX

Explanations

occurrences of the preposition "to."

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

izr

-0.16

immers

-0.15

 xuyÃªn

-0.15

otty

-0.14

Ã¶y

-0.14

icana

-0.14

/we

-0.14

íĢ

-0.14

-Sah

-0.14

_THREAD

-0.14

POSITIVE LOGITS

iker

0.16

alim

0.15

-the

0.15

 intrinsic

0.15

ef

0.14

ycz

0.14

 Anders

0.14

 Percy

0.13

mage

0.13

isin

0.13

Activations Density 0.407%

occurrences of the preposition "to."

No Comments

No Known Activations