INDEX

Explanations

references to software development concepts and processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

.generated

-0.17

engo

-0.15

ingles

-0.14

Fay

-0.14

arro

-0.14

ramer

-0.14

 Zucker

-0.14

raig

-0.14

ullo

-0.14

 conduct

-0.14

POSITIVE LOGITS

.tex

0.22

.gnu

0.20

ï¼ł

0.18

 Affero

0.18

Äįet

0.16

_TEX

0.16

bfd

0.16

 Lesser

0.15

Invariant

0.15

.sav

0.15

Activations Density 0.044%

references to software development concepts and processes

No Comments

No Known Activations