INDEX

Explanations

expressions of surprise or disbelief regarding unexpected achievements or situations

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

umas

-0.17

.scalablytyped

-0.17

efe

-0.15

ëĦĲ

-0.14

 UIStoryboard

-0.14

 rand

-0.14

rand

-0.14

ìĦŃ

-0.14

 infer

-0.14

avaÅŁ

-0.14

POSITIVE LOGITS

 never

0.31

Never

0.28

 NEVER

0.28

 Never

0.28

never

0.25

 thought

0.25

 Thought

0.23

 nunca

0.23

 least

0.21

thought

0.21

Activations Density 0.104%

expressions of surprise or disbelief regarding unexpected achievements or situations

No Comments

No Known Activations