INDEX

Explanations

references to measurements or classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

Fore

-0.15

Borders

-0.15

 Tall

-0.15

cken

-0.15

IFO

-0.15

çīĩ

-0.14

chal

-0.14

ãĤĩãģĨ

-0.14

oscope

-0.14

istring

-0.14

POSITIVE LOGITS

hoff

0.17

0.15

(DWORD

0.15

Ø·ÙĬ

0.15

 dest

0.14

 diplom

0.14

 hold

0.14

ups

0.14

 found

0.14

0.13

Activations Density 0.042%

references to measurements or classifications

No Comments

No Known Activations