INDEX

Explanations

citations or credits within the document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

Ã¡la

-0.16

bor

-0.15

 hereby

-0.15

ëĭ¨

-0.15

cts

-0.14

AMS

-0.14

åĿª

-0.14

á»©t

-0.14

_gp

-0.14

inha

-0.14

POSITIVE LOGITS

áº¹n

0.16

enville

0.16

spender

0.14

KR

0.14

zon

0.14

odem

0.14

ignal

0.14

leigh

0.14

ucu

0.14

Activations Density 0.003%

citations or credits within the document

No Comments

No Known Activations