INDEX

Explanations

programming code structures and syntax elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

aper

-0.15

odash

-0.15

omo

-0.15

activex

-0.15

APER

-0.15

ought

-0.15

rale

-0.15

ben

-0.14

sv

-0.14

æ²¢

-0.14

POSITIVE LOGITS

ulti

0.15

à¥įà¤¯à¤µà¤¸

0.14

Ĭ

0.14

@class

0.14

orida

0.14

_EVT

0.14

Ced

0.13

pto

0.13

Ø¢ÙħØ¯

0.13

ToFile

0.13

Activations Density 0.055%

programming code structures and syntax elements

No Comments

No Known Activations