INDEX

Explanations

references to national institutions and policies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

ude

-0.17

bread

-0.16

ker

-0.15

bob

-0.14

*&

-0.14

 Webcam

-0.13

zik

-0.13

noticed

-0.13

ä¸įæĸŃ

-0.13

POSITIVE LOGITS

-level

0.20

-Owned

0.18

-Level

0.17

 Minor

0.16

anzi

0.16

-owned

0.16

gesi

0.16

 '\''

0.15

ledge

0.15

 addCriterion

0.15

Activations Density 0.035%

references to national institutions and policies

No Comments

No Known Activations