INDEX

Explanations

references to the Oxford English Dictionary and its significance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

translated

-0.18

Translated

-0.16

è¯ĳ

-0.16

loor

-0.16

quals

-0.15

ardown

-0.15

 shorthand

-0.15

occo

-0.15

interpre

-0.14

enburg

-0.14

POSITIVE LOGITS

 usage

0.20

 Usage

0.20

 dictionary

0.20

 morphology

0.20

Usage

0.20

 USAGE

0.18

 Dictionary

0.18

usage

0.18

USAGE

0.18

dictionary

0.17

Activations Density 0.100%

references to the Oxford English Dictionary and its significance

No Comments

No Known Activations