INDEX

Explanations

phrases indicating growth, importance, or increasing trends in various contexts

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

uri

-0.16

kke

-0.16

ØªØ§Ø¨

-0.15

isle

-0.15

aura

-0.14

::

-0.14

kp

-0.14

kus

-0.14

ChangeListener

-0.14

inae

-0.14

POSITIVE LOGITS

 becoming

0.21

ly

0.19

 increasingly

0.18

 become

0.16

ening

0.15

LY

0.15

 importance

0.14

 è¶

0.14

/gtest

0.14

 becomes

0.14

Activations Density 0.034%

phrases indicating growth, importance, or increasing trends in various contexts

No Comments

No Known Activations