INDEX

Explanations

concepts related to complexity and nuances in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

 EÅŁ

-0.17

ysz

-0.17

(s

-0.16

out

-0.15

words

-0.15

ingu

-0.15

zi

-0.15

ach

-0.14

ings

-0.14

iao

-0.14

POSITIVE LOGITS

gger

0.18

ously

0.16

ustil

0.15

odel

0.15

esterday

0.14

 quot

0.14

sar

0.14

flex

0.13

estar

0.13

TargetException

0.13

Activations Density 0.452%

concepts related to complexity and nuances in various contexts

No Comments

No Known Activations