INDEX

Explanations

instructions related to clicking links or buttons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

aida

-0.18

oner

-0.15

eprom

-0.15

ãĥĭãĤ¢

-0.15

etim

-0.14

ibia

-0.14

 Dickinson

-0.14

misc

-0.14

fi

-0.14

anda

-0.13

POSITIVE LOGITS

 links

0.19

 icons

0.19

 icon

0.17

 link

0.17

 name

0.17

 desired

0.16

icons

0.16

desired

0.16

 Icon

0.16

Cog

0.15

Activations Density 0.042%

instructions related to clicking links or buttons

No Comments

No Known Activations