INDEX

Explanations

data related to scientific research and measurement outcomes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

letal

-0.17

kla

-0.14

 pony

-0.14

tog

-0.14

 Bonds

-0.14

thro

-0.14

ìľ¨

-0.14

odÄĽ

-0.13

ignet

-0.13

^K

-0.13

POSITIVE LOGITS

 fear

0.22

 learned

0.20

 reward

0.20

 Consolid

0.20

 learning

0.20

 Learned

0.20

 Morris

0.20

 locom

0.20

 licking

0.19

 wheel

0.19

Activations Density 0.016%

data related to scientific research and measurement outcomes

No Comments

No Known Activations