INDEX

Explanations

references to technology and software applications

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

-0.17

omi

-0.15

 Greenland

-0.15

Ħ

-0.14

ozo

-0.14

 NavParams

-0.14

STYPE

-0.13

COORD

-0.13

POSITIVE LOGITS

ToWorld

0.18

_tele

0.16

Beh

0.15

aeper

0.14

Beh

0.14

inta

0.14

istrovstvÃŃ

0.14

Ð±Ð°Ð²

0.14

assis

0.13

Exc

0.13

Activations Density 0.028%

references to technology and software applications

No Comments

No Known Activations