INDEX

Explanations

occurrences of the word "on."

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

ike

-0.16

inine

-0.15

lean

-0.15

åķĨ

-0.14

 lean

-0.13

Ã¨o

-0.13

under

-0.13

rag

-0.13

POSITIVE LOGITS

INCLUDING

0.17

 Allen

0.16

 -*-č↵

0.15

.scalablytyped

0.15

Allen

0.15

 skoro

0.15

RectTransform

0.14

ColumnsMode

0.14

iffer

0.14

ä¸Ģèµ·

0.14

Activations Density 0.002%

occurrences of the word "on."

No Comments

No Known Activations