INDEX

Explanations

terms related to historical and philosophical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

AFX

-0.15

Î¼Î·

-0.15

ÑĪÐ¸Ð»Ð°

-0.14

ÃĹ↵↵

-0.14

 Jerseys

-0.14

erez

-0.14

 Nurs

-0.14

POSITIVE LOGITS

 ÙĨØ³Ø¨

0.16

than

0.14

ypad

0.14

 parÃ§asÄ±

0.14

hum

0.14

 æ½

0.13

×Ĺ

0.13

Verdana

0.13

ushima

0.13

gui

0.13

Activations Density 0.257%

terms related to historical and philosophical contexts

No Comments

No Known Activations