INDEX

Explanations

expressions of happiness or satisfaction

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

orro

-0.16

ersh

-0.16

erap

-0.15

oss

-0.15

aso

-0.14

erk

-0.14

.tests

-0.13

pile

-0.13

_maximum

-0.13

Unsigned

-0.13

POSITIVE LOGITS

ness

0.19

 someone

0.18

 overall

0.17

 finally

0.17

ully

0.17

lich

0.17

ewater

0.16

 somebody

0.16

acre

0.16

dest

0.16

Activations Density 0.033%

expressions of happiness or satisfaction

No Comments

No Known Activations