INDEX

Explanations

instances of significant numerical values or timestamps

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

-0.15

vit

-0.15

Rus

-0.14

ÑĳÑĢ

-0.14

EP

-0.14

roi

-0.14

 Richt

-0.14

 Verd

-0.14

serir

-0.13

POSITIVE LOGITS

oha

0.15

gamber

0.15

osl

0.15

alars

0.15

 casc

0.15

isposable

0.14

igid

0.14

.DisplayStyle

0.14

getManager

0.14

croft

0.14

Activations Density 0.037%

instances of significant numerical values or timestamps

No Comments

No Known Activations