INDEX

Explanations

terms related to structured systems and their effects or qualities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

affen

-0.17

-alist

-0.16

vt

-0.15

brtc

-0.14

aub

-0.14

eldon

-0.14

erli

-0.14

renom

-0.14

ÏīÏĥÎ·

-0.14

POSITIVE LOGITS

isoft

0.15

activex

0.14

PLIT

0.14

mav

0.14

 Rowe

0.13

ifest

0.13

 Guth

0.13

acular

0.13

Activations Density 0.062%

terms related to structured systems and their effects or qualities

No Comments

No Known Activations