INDEX

Explanations

mentions of different layouts or configurations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

 Harvey

-0.15

iny

-0.14

iqueta

-0.14

Gal

-0.14

è¦§

-0.14

IData

-0.14

bow

-0.14

ork

-0.14

_FMT

-0.14

dow

-0.13

POSITIVE LOGITS

tee

0.17

arna

0.17

.eof

0.16

itlement

0.15

ernaut

0.15

strup

0.15

anja

0.15

rant

0.15

caf

0.15

Activations Density 0.004%

mentions of different layouts or configurations

No Comments

No Known Activations