INDEX

Explanations

references to formal processes and documentation in a structured context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

elli

-0.15

ekt

-0.14

PROTO

-0.14

ÑĢÐµÐ¹

-0.14

Ð°ÑĤÐµ

-0.13

 neob

-0.13

 adulti

-0.13

zion

-0.13

EIF

-0.13

POSITIVE LOGITS

dee

0.16

ÑĥÑĢÑĥ

0.15

rray

0.15

ebb

0.14

ium

0.14

 discrim

0.14

omon

0.14

ahi

0.14

.Areas

0.14

poons

0.13

Activations Density 0.020%

references to formal processes and documentation in a structured context

No Comments

No Known Activations