INDEX

Explanations

terms associated with modification or transformation processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

 Furniture

-0.17

ntag

-0.15

aji

-0.15

 furniture

-0.15

anta

-0.15

juven

-0.14

*)((

-0.14

#End

-0.14

 Amir

-0.13

CHIP

-0.13

POSITIVE LOGITS

anh

0.15

ecess

0.14

enia

0.14

iais

0.14

_linked

0.14

 Hund

0.13

 wheels

0.13

ìĬ¤íģ¬

0.13

sti

0.13

ä¾Ľ

0.13

Activations Density 0.001%

terms associated with modification or transformation processes

No Comments

No Known Activations