INDEX

Explanations

open parentheses and their context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

Ð»Ð¸Ð²

-0.15

ozo

-0.14

oS

-0.14

mes

-0.14

_lazy

-0.14

abcdefghijklmnop

-0.13

ãĥ¬ãĤ¹

-0.13

 Rear

-0.13

lingen

-0.13

POSITIVE LOGITS

agne

0.17

zdy

0.15

antic

0.14

Maj

0.14

æĤŁ

0.14

odes

0.13

iface

0.13

aim

0.13

 scaleY

0.13

akin

0.13

Activations Density 0.111%

open parentheses and their context

No Comments

No Known Activations