INDEX

Explanations

terms related to interventions and support systems

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

quer

-0.17

é½

-0.16

alar

-0.15

aggi

-0.15

ness

-0.15

 Ð¿ÑĢÐ¾Ð¼Ð¸ÑģÐ»Ð¾Ð²

-0.14

 Lawson

-0.14

gy

-0.14

AML

-0.13

/Library

-0.13

POSITIVE LOGITS

Ð¢Ðŀ

0.15

aye

0.15

eru

0.14

jos

0.14

RAINT

0.14

entions

0.13

fromJson

0.13

 heav

0.13

urous

0.13

.Foundation

0.13

Activations Density 0.006%

terms related to interventions and support systems

No Comments

No Known Activations