INDEX

Explanations

terms related to the concept of "av."

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

iya

-0.19

iyas

-0.19

-0.18

ificio

-0.17

apter

-0.17

enie

-0.16

ãĥ©ãĤ¤ãĥĪ

-0.16

iage

-0.15

auf

-0.15

iap

-0.14

POSITIVE LOGITS

olution

0.21

akening

0.18

irtual

0.17

oxel

0.17

ski

0.17

oe

0.17

etter

0.17

olumes

0.17

est

0.16

ÄĽt

0.16

Activations Density 0.039%

terms related to the concept of "av."

No Comments

No Known Activations