INDEX

Explanations

references to internal systems or processes

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

ioc

-0.17

ois

-0.15

nish

-0.14

Ø§ÙģØª

-0.14

-shaped

-0.14

redient

-0.14

iability

-0.14

ableView

-0.14

alyzer

-0.14

bai

-0.14

POSITIVE LOGITS

/Internal

0.40

/internal

0.33

.Internal

0.24

izado

0.23

ized

0.22

/ext

0.21

halb

0.21

(internal

0.21

 Affairs

0.20

most

0.20

Activations Density 0.030%

references to internal systems or processes

No Comments

No Known Activations