INDEX

Explanations

references to the current state or condition of something

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

 Morav

-0.16

æľºä¼ļ

-0.15

atto

-0.15

TestFixture

-0.15

.scalablytyped

-0.14

æĻ¨

-0.14

ÄĽj

-0.14

 )↵↵↵↵↵↵↵↵

-0.14

 Holden

-0.14

acid

-0.13

POSITIVE LOGITS

 cach

0.17

é¼

0.15

 cache

0.15

bjerg

0.15

Ð¾ÑĢÐ¾ÑĪ

0.14

cache

0.14

blink

0.14

istically

0.14

ema

0.14

ÐµÑĢÑĮ

0.14

Activations Density 0.161%

references to the current state or condition of something

No Comments

No Known Activations