INDEX

Explanations

numerical values or counts related to operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

ayet

-0.15

ield

-0.15

ynÄ±

-0.15

ocket

-0.14

kud

-0.14

multiline

-0.14

//**↵

-0.14

stoff

-0.14

steder

-0.13

_mi

-0.13

POSITIVE LOGITS

0.15

ingu

0.15

æ¯

0.14

Ļ

0.14

otts

0.14

_USB

0.14

itos

0.14

Activations Density 0.065%

numerical values or counts related to operations

No Comments

No Known Activations