INDEX

Explanations

terms associated with organizations, especially in the arts and sciences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

aurus

-0.18

asca

-0.17

ryn

-0.16

fox

-0.15

lund

-0.14

udd

-0.14

oldown

-0.14

urous

-0.14

Soup

-0.14

licher

-0.14

POSITIVE LOGITS

 Lois

0.16

 Provid

0.15

 sadd

0.15

nn

0.14

ipel

0.14

 Finder

0.14

åŃ¦ä¼ļ

0.14

å£«

0.14

 Establishment

0.13

Activations Density 0.165%

terms associated with organizations, especially in the arts and sciences

No Comments

No Known Activations