INDEX

Explanations

specific programming syntax and organizational terms

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ÙħØ³

-0.15

handleRequest

-0.14

ophon

-0.14

Î®ÏĤ

-0.14

zed

-0.14

 Preservation

-0.14

vertiser

-0.14

INGER

-0.14

abez

-0.13

rase

-0.13

POSITIVE LOGITS

Builders

0.15

avar

0.15

emale

0.15

 Malone

0.15

 Duch

0.14

ulen

0.14

à¹Ģà¸«à¸¥

0.14

ult

0.14

viar

0.14

.getWriter

0.14

Activations Density 0.007%

specific programming syntax and organizational terms

No Comments

No Known Activations