INDEX

Explanations

questions and instructions directed at the reader

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

Ð¾ÑĤÑĢÐµÐ±

-0.16

/repos

-0.16

à¸µà¸¢à¸£

-0.15

eli

-0.14

ivy

-0.14

ãĥ³ãĥĨ

-0.14

laus

-0.14

sti

-0.14

 Ster

-0.13

POSITIVE LOGITS

 Giang

0.15

OA

0.15

odyn

0.14

GC

0.14

enes

0.14

 preventive

0.14

å¢

0.13

SED

0.13

HORT

0.13

ULE

0.13

Activations Density 0.221%

questions and instructions directed at the reader

No Comments

No Known Activations