INDEX

Explanations

code snippets or references to programming functions and expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

uras

-0.15

ÑĢÐ°ÑĤ

-0.14

dig

-0.14

izen

-0.14

ÑģÐµÑĢ

-0.14

earn

-0.13

 Strand

-0.13

tem

-0.13

 Shine

-0.13

ella

-0.13

POSITIVE LOGITS

 outputs

0.20

#=>

0.19

 output

0.19

 Output

0.19

outputs

0.18

 Outputs

0.17

 result

0.17

 OUTPUT

0.17

ãģĻãĤĭãģ¨

0.17

OUTPUT

0.17

Activations Density 0.068%

code snippets or references to programming functions and expressions

No Comments

No Known Activations