INDEX

Explanations

terms related to online platforms and their functionalities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

oty

-0.16

 posit

-0.15

nik

-0.15

arth

-0.14

emme

-0.14

Ãºp

-0.14

aff

-0.14

 Late

-0.14

nation

-0.14

requ

-0.13

POSITIVE LOGITS

 cÄĥ

0.20

 Ã®

0.20

 acest

0.20

 Ã®nt

0.20

 Ã®n

0.20

 fost

0.19

doi

0.18

 rezerv

0.18

dou

0.18

sf

0.18

Activations Density 0.025%

terms related to online platforms and their functionalities

No Comments

No Known Activations