INDEX

Explanations

instances of emotional reactions and discussions related to personal experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

acco

-0.15

ÑĬ

-0.15

udge

-0.15

åħĥ

-0.14

-0.13

adiator

-0.13

aja

-0.13

ilden

-0.13

APT

-0.13

POSITIVE LOGITS

Ø¨Ø´

0.17

eydi

0.16

è½

0.15

ENCHMARK

0.14

ãĤ¤ãĤ¯

0.14

.Localization

0.14

ìĨ

0.13

Å¾

0.13

icut

0.13

UZ

0.13

Activations Density 0.677%

instances of emotional reactions and discussions related to personal experiences

No Comments

No Known Activations