INDEX

Explanations

references to rare or significant occurrences and emotional responses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

allery

-0.14

 onBind

-0.14

adaki

-0.14

esco

-0.14

ë»

-0.13

adlo

-0.13

kÃ¡

-0.13

neutral

-0.13

URRED

-0.13

åĽº

-0.13

POSITIVE LOGITS

 rare

1.13

 rarity

1.03

 Rare

0.94

Rare

0.90

 uncommon

0.71

rar

0.66

 Rarity

0.62

 scarce

0.55

 ÑĢÐµÐ´

0.55

 rarely

0.48

Activations Density 0.249%

references to rare or significant occurrences and emotional responses

No Comments

No Known Activations