INDEX

Explanations

references to interviews and discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

cha

-0.17

 resident

-0.15

amb

-0.15

IV

-0.15

iec

-0.15

 Form

-0.15

ic

-0.14

ÑĸÑĶ

-0.14

Dem

-0.14

as

-0.14

POSITIVE LOGITS

UILTIN

0.18

ÅĻÃŃÅ¾

0.16

uiltin

0.16

ulings

0.15

.scalablytyped

0.15

ÑħÐ¸

0.15

lm

0.15

LEGRO

0.15

olib

0.15

eatures

0.15

Activations Density 0.347%

references to interviews and discussions

No Comments

No Known Activations