INDEX

Explanations

mentions of the name Warren, particularly in relation to Warren Buffett

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

itude

-0.16

tn

-0.16

SEG

-0.15

ondon

-0.15

er

-0.15

ãĥĨãĥ«

-0.15

SEP

-0.15

itter

-0.14

gel

-0.14

erne

-0.14

POSITIVE LOGITS

tach

0.17

 Hath

0.16

eci

0.16

ä¸Ī

0.16

ivet

0.16

prung

0.15

egra

0.15

 Buffett

0.15

sville

0.14

ÑĥÐ¹

0.14

Activations Density 0.012%

mentions of the name Warren, particularly in relation to Warren Buffett

No Comments

No Known Activations