INDEX

Explanations

elements related to numeric values and formatting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

IQ

-0.14

 Graz

-0.14

cret

-0.14

[$_

-0.13

fty

-0.13

 nationalism

-0.13

anken

-0.13

CHIP

-0.13

RuntimeObject

-0.13

orum

-0.13

POSITIVE LOGITS

utow

0.15

ober

0.14

eru

0.14

ooth

0.14

argar

0.14

ãĥ³ãĥģ

0.13

omore

0.13

abor

0.13

 same

0.13

UTOR

0.13

Activations Density 0.145%

elements related to numeric values and formatting

No Comments

No Known Activations