INDEX

Explanations

phrases or prepositions related to dependencies and conditions

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

amburger

-0.14

postalcode

-0.14

OCUMENT

-0.13

shaw

-0.13

imens

-0.13

ilet

-0.13

abant

-0.13

 pageNo

-0.13

hesive

-0.13

ware

-0.13

POSITIVE LOGITS

 whether

0.14

fen

0.14

 Ð¶Ðµ

0.14

 alien

0.14

IntPtr

0.13

à¥Įà¤²

0.13

/native

0.13

çĳŁ

0.13

 vintage

0.13

 stage

0.13

Activations Density 0.028%

phrases or prepositions related to dependencies and conditions

No Comments

No Known Activations