INDEX

Explanations

timestamps and numerical data

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

avic

-0.19

RU

-0.16

elli

-0.15

ause

-0.15

el

-0.14

slash

-0.14

eil

-0.14

ensis

-0.14

LSM

-0.14

POSITIVE LOGITS

/copyleft

0.16

ewidth

0.15

ãģ¥

0.15

estone

0.15

vÄĽt

0.14

éŁ¿

0.14

fak

0.14

.trailing

0.14

ë²

0.14

 DISCLAIM

0.14

Activations Density 0.004%

timestamps and numerical data

No Comments

No Known Activations