INDEX

Explanations

occurrences of the word "remember" and related phrases indicating recollection or experience

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

 loud

-0.17

 Jewel

-0.16

rel

-0.16

.aspx

-0.15

Â·

-0.15

ddb

-0.15

 broad

-0.15

 Jacqu

-0.15

 Broad

-0.14

 Loud

-0.14

POSITIVE LOGITS

éĳĳ

0.17

éĮ

0.16

DownList

0.15

ugar

0.15

isman

0.14

Riv

0.14

rove

0.14

iphy

0.14

getColumn

0.14

çº¦

0.14

Activations Density 0.281%

occurrences of the word "remember" and related phrases indicating recollection or experience

No Comments

No Known Activations