INDEX

Explanations

technical terms related to programming and data types

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

cher

-0.16

.fil

-0.16

figcaption

-0.16

veal

-0.15

defs

-0.15

_consts

-0.15

dsp

-0.14

 Pruitt

-0.14

usra

-0.14

æľºæŀĦ

-0.14

POSITIVE LOGITS

Hus

0.17

 Adler

0.16

agna

0.15

Loy

0.15

eling

0.14

 Diet

0.14

 Scha

0.14

 Bene

0.14

Ear

0.14

Activations Density 0.004%

technical terms related to programming and data types

No Comments

No Known Activations