INDEX

Explanations

terms related to historical context and social discussions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

agon

-0.16

è«

-0.16

ovsky

-0.14

AGON

-0.14

empo

-0.14

ono

-0.13

xec

-0.13

apon

-0.13

ONO

-0.13

ories

-0.13

POSITIVE LOGITS

ernes

0.15

quia

0.14

ippets

0.14

ovÄĽ

0.14

amic

0.14

eph

0.13

 news

0.13

ÐºÑĥÑĢ

0.13

Ú¯Ø§ÙĩÛĮ

0.13

Activations Density 0.251%

terms related to historical context and social discussions

No Comments

No Known Activations