INDEX

Explanations

references to educational programs and their attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

err

-0.15

æ¸Ī

-0.15

awn

-0.15

.opens

-0.14

URRE

-0.14

xDB

-0.14

 Dort

-0.14

alar

-0.14

morph

-0.14

urre

-0.14

POSITIVE LOGITS

shaw

0.16

matic

0.15

phis

0.14

-urlencoded

0.14

swick

0.14

 MANUAL

0.14

herits

0.14

ston

0.14

atically

0.14

oty

0.14

Activations Density 0.046%

references to educational programs and their attributes

No Comments

No Known Activations