INDEX

Explanations

terms related to organizational changes and mergers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

 KrÃ¡l

-0.15

ewis

-0.14

ewan

-0.14

AYOUT

-0.14

zeich

-0.14

oken

-0.14

 Bloc

-0.14

Bloc

-0.14

 eskort

-0.13

ayd

-0.13

POSITIVE LOGITS

 merged

0.20

merged

0.20

åĲĪ

0.19

 merging

0.19

 merger

0.18

 merge

0.18

 merges

0.17

 íķ©

0.17

0.16

 fuse

0.16

Activations Density 0.058%

terms related to organizational changes and mergers

No Comments

No Known Activations