INDEX

Explanations

references to technology and its various implementations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

udy

-0.17

 ActionTypes

-0.17

hide

-0.17

itsu

-0.15

itre

-0.15

atter

-0.15

unct

-0.14

iment

-0.14

ding

-0.14

steller

-0.14

POSITIVE LOGITS

/software

0.21

ies

0.19

ically

0.19

/engine

0.18

IES

0.17

ologically

0.16

reamble

0.15

ologies

0.15

rical

0.15

/media

0.15

Activations Density 0.059%

references to technology and its various implementations

No Comments

No Known Activations