INDEX

Explanations

instances of the word "forward" and related terms indicating progress or advancement

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

hetto

-0.16

 reluct

-0.15

eral

-0.15

utes

-0.14

kou

-0.14

imas

-0.14

 shar

-0.14

plete

-0.14

 Minute

-0.14

ks

-0.14

POSITIVE LOGITS

/back

0.27

wards

0.18

forward

0.18

QUIRES

0.18

-forward

0.18

-thinking

0.17

/down

0.17

warf

0.17

ward

0.17

 forward

0.16

Activations Density 0.037%

instances of the word "forward" and related terms indicating progress or advancement

No Comments

No Known Activations