INDEX

Explanations

words and phrases related to geographical locations and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

igo

-0.17

 orders

-0.16

 Clarkson

-0.15

iate

-0.15

&C

-0.14

HWND

-0.14

imps

-0.14

 Empty

-0.14

ulas

-0.14

 Indy

-0.14

POSITIVE LOGITS

artz

0.17

arb

0.16

rchive

0.16

STYPE

0.15

 ngang

0.15

 carte

0.15

ORA

0.15

ng

0.15

quette

0.14

lington

0.14

Activations Density 0.013%

words and phrases related to geographical locations and measurements

No Comments

No Known Activations