INDEX

Explanations

code-related functions and operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

enor

-0.19

è

-0.16

eli

-0.15

odi

-0.15

QL

-0.14

sv

-0.14

imest

-0.14

.hy

-0.14

ling

-0.14

uess

-0.14

POSITIVE LOGITS

 Invent

0.15

whe

0.15

 Mess

0.15

owell

0.15

imas

0.15

Mess

0.15

lal

0.15

posium

0.15

fon

0.14

alace

0.14

Activations Density 0.246%

code-related functions and operations

No Comments

No Known Activations