INDEX

Explanations

references to various types of equipment

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ucas

-0.18

ese

-0.15

aron

-0.15

cce

-0.15

cname

-0.14

xdc

-0.14

Ð¾ÑģÑĮ

-0.13

/export

-0.13

/global

-0.13

ivers

-0.13

POSITIVE LOGITS

rement

0.19

mtree

0.17

ally

0.17

sel

0.16

/software

0.16

ils

0.16

eller

0.15

sl

0.15

Activations Density 0.020%

references to various types of equipment

No Comments

No Known Activations