INDEX

Explanations

snippets of code or programming-related questions and answers

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

asca

-0.16

iar

-0.16

 Suddenly

-0.15

asc

-0.15

 suddenly

-0.14

rÃ³

-0.14

 innoc

-0.14

ubit

-0.14

esis

-0.13

BUG

-0.13

POSITIVE LOGITS

 currently

0.18

 tried

0.18

ÑģÐºÐ»Ð°Ð´

0.18

 Currently

0.17

 attempted

0.17

currently

0.17

å°

0.16

 Tried

0.15

 accomplish

0.15

 Prel

0.15

Activations Density 0.105%

snippets of code or programming-related questions and answers

No Comments

No Known Activations