INDEX

Explanations

terms associated with responses and reactions to situations or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

ouz

-0.16

atter

-0.15

esen

-0.15

ern

-0.15

enza

-0.15

 phÃ³ng

-0.14

.Persistent

-0.14

ãĥ¼ãĥ

-0.14

elters

-0.14

POSITIVE LOGITS

ivate

0.41

aries

0.28

ively

0.25

iveness

0.24

/response

0.24

ives

0.23

/respond

0.21

ual

0.20

ivated

0.20

ivity

0.20

Activations Density 0.020%

terms associated with responses and reactions to situations or events

No Comments

No Known Activations