INDEX

Explanations

expressions of habitual or consistent behaviors or tendencies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

adia

-0.18

aving

-0.17

ime

-0.17

isans

-0.15

esan

-0.15

icism

-0.15

ansa

-0.15

å¥ı

-0.15

oste

-0.15

nie

-0.15

POSITIVE LOGITS

erness

0.26

 toward

0.21

entially

0.19

 towards

0.19

 tend

0.17

ENCIES

0.16

entious

0.16

 tends

0.16

±Ð¾ÑĤ

0.15

Towards

0.15

Activations Density 0.011%

expressions of habitual or consistent behaviors or tendencies

No Comments

No Known Activations