INDEX

Explanations

instances of the word "follow" and its variations, indicating a focus on themes of following or guidance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

arts

-0.17

akash

-0.16

\<^

-0.15

-Token

-0.15

aled

-0.15

nder

-0.14

efeller

-0.14

OfYear

-0.14

olum

-0.14

pras

-0.14

POSITIVE LOGITS

 closely

0.20

izard

0.18

iston

0.17

.follow

0.16

follow

0.15

 Follow

0.15

Obr

0.14

cone

0.14

Follow

0.14

Activations Density 0.088%

instances of the word "follow" and its variations, indicating a focus on themes of following or guidance

No Comments

No Known Activations