INDEX

Explanations

references to banks and banking-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

aneous

-0.17

ÏĢÎ¯

-0.16

eru

-0.16

aÅŁ

-0.15

rah

-0.15

yk

-0.15

mente

-0.15

rvine

-0.14

loff

-0.14

angep

-0.14

POSITIVE LOGITS

ruptcy

0.20

rupt

0.18

oven

0.17

roll

0.16

grades

0.15

aged

0.15

arios

0.15

yard

0.15

/devices

0.15

ilde

0.15

Activations Density 0.026%

references to banks and banking-related terms

No Comments

No Known Activations