INDEX

Explanations

references to structures and categories in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

.scalablytyped

-0.14

istrovstvÃŃ

-0.13

Ð»Ð¸ÑĪÐºÐ¾Ð¼

-0.13

strument

-0.13

od

-0.13

JsonValue

-0.13

iven

-0.13

Éµ

-0.13

-dominated

-0.13

 åĳ

-0.12

POSITIVE LOGITS

opp

0.17

Ã¡o

0.17

ivas

0.16

etas

0.15

amble

0.15

vais

0.15

 initWithStyle

0.15

erif

0.15

illez

0.14

 Schwarz

0.14

Activations Density 0.104%

references to structures and categories in various contexts

No Comments

No Known Activations