INDEX

Explanations

elements related to programming and technical instructions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

ego

-0.15

_SID

-0.15

kest

-0.15

elson

-0.15

 Tong

-0.14

ÐµÑĢÐ³

-0.14

asley

-0.14

igo

-0.14

modifiable

-0.14

odu

-0.14

POSITIVE LOGITS

Har

0.25

Har

0.25

har

0.23

har

0.23

HAR

0.20

Ref

0.20

Ref

0.20

UM

0.20

ref

0.19

umb

0.19

Activations Density 0.031%

elements related to programming and technical instructions

No Comments

No Known Activations

elements related to programming and technical instructions

No Comments

No Known Activations