INDEX

Explanations

programming language syntax and structure

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

 Zahl

-0.15

æ°ĳ

-0.14

abol

-0.14

onom

-0.13

 Civic

-0.13

 recl

-0.13

 Jets

-0.13

antan

-0.13

[url

-0.13

atron

-0.13

POSITIVE LOGITS

#line

0.17

.Slice

0.17

omor

0.17

ype

0.16

arih

0.16

 sling

0.15

mscorlib

0.14

ucus

0.14

imos

0.14

anel

0.14

Activations Density 0.003%

programming language syntax and structure

No Comments

No Known Activations