INDEX

Explanations

numerical data and references to locations and events

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

igu

-0.18

atu

-0.18

ensa

-0.17

ÑģÑĤÐ¸Ð½

-0.16

Ð¸Ð¼Ñĥ

-0.15

idan

-0.15

ascar

-0.15

ota

-0.15

inas

-0.14

verige

-0.14

POSITIVE LOGITS

ëĭ´

0.14

URN

0.14

irting

0.14

ofire

0.14

ocos

0.14

çĵ¦

0.14

mi

0.14

 margin

0.13

 Homer

0.13

 acceso

0.13

Activations Density 0.454%

numerical data and references to locations and events

No Comments

No Known Activations