INDEX

Explanations

structures and properties of JSON data

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

lear

-0.15

bob

-0.15

ilities

-0.15

kk

-0.15

âĢ¦

-0.15

lop

-0.14

illed

-0.14

lech

-0.14

zens

-0.14

ÅĽ

-0.14

POSITIVE LOGITS

aday

0.15

 Stall

0.15

":""

0.14

Ø±ÙĪÙĩ

0.14

 Sail

0.14

arella

0.14

*'

0.14

 Shea

0.14

reesome

0.14

 çĽ¸

0.14

Activations Density 0.138%

structures and properties of JSON data

No Comments

No Known Activations