INDEX

Explanations

occurrences of specific prepositions and phrases indicating location or context in sentences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

asca

-0.15

##_

-0.14

ÑģÐ»Ð¸

-0.14

owski

-0.14

nea

-0.14

acao

-0.13

aways

-0.13

’ÑıÑĤ

-0.13

lica

-0.13

ãĥ³ãĥĸ

-0.13

POSITIVE LOGITS

_TERMIN

0.14

asin

0.13

eel

0.13

arda

0.13

iele

0.13

 mushroom

0.13

ÙģÙĩ

0.12

ako

0.12

 itemType

0.12

olut

0.12

Activations Density 0.334%

occurrences of specific prepositions and phrases indicating location or context in sentences

No Comments

No Known Activations