INDEX

Explanations

mathematical symbols and notations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

igon

-0.16

enez

-0.15

ault

-0.14

KER

-0.14

oku

-0.14

gni

-0.14

cox

-0.14

loe

-0.14

mour

-0.14

olar

-0.14

POSITIVE LOGITS

fab

0.16

0.15

aries

0.14

bra

0.14

 Goods

0.14

0.13

iest

0.13

_deinit

0.13

Activations Density 0.141%

mathematical symbols and notations

No Comments

No Known Activations