INDEX

Explanations

entities related to numerical or statistical data

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

lement

-0.15

-svg

-0.15

ement

-0.14

em

-0.14

Ð¸ÑĦ

-0.14

ful

-0.14

aver

-0.14

ifi

-0.14

aut

-0.14

 exerc

-0.14

POSITIVE LOGITS

atest

0.17

quo

0.17

 intptr

0.15

odiac

0.15

 Terminal

0.15

ÙĪØ§Ø±Ùĩ

0.15

oned

0.15

dorf

0.15

Ð¾ÑĢÑĤ

0.14

Activations Density 0.065%

entities related to numerical or statistical data

No Comments

No Known Activations