INDEX

Explanations

words related to amplifying, increasing, or elevating concepts, especially in contexts of actions or attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

er

-0.20

Ø±

-0.18

RF

-0.18

berman

-0.17

rnd

-0.17

lsen

-0.17

-0.16

rand

-0.15

por

-0.15

lad

-0.15

POSITIVE LOGITS

stead

0.21

shire

0.20

ylon

0.19

arts

0.18

site

0.18

ster

0.17

ithe

0.16

elier

0.16

agne

0.15

Activations Density 0.034%

words related to amplifying, increasing, or elevating concepts, especially in contexts of actions or attributes

No Comments

No Known Activations