INDEX

Explanations

terms related to flowers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

avel

-0.15

orial

-0.14

adera

-0.14

Ã²n

-0.14

latlong

-0.14

TING

-0.14

AE

-0.14

eo

-0.14

ibi

-0.14

 proven

-0.13

POSITIVE LOGITS

uml

0.15

than

0.15

ery

0.14

.nano

0.14

aned

0.14

issant

0.14

ipo

0.14

ī

0.14

like

0.14

odi

0.14

Activations Density 0.017%

terms related to flowers

No Comments

No Known Activations