INDEX

Explanations

references to publications and academic conferences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

hai

-0.15

 procedure

-0.15

eyse

-0.15

-0.14

 Grande

-0.14

oker

-0.14

 process

-0.14

Ð°ÑĩÐµ

-0.14

ker

-0.14

 curious

-0.13

POSITIVE LOGITS

azo

0.16

nes

0.14

umer

0.14

chaft

0.13

eed

0.13

(Function

0.13

Lets

0.13

 ..."

0.13

 Lets

0.13

imit

0.13

Activations Density 0.011%

references to publications and academic conferences

No Comments

No Known Activations