INDEX

Explanations

words related to architectural terms and structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

ene

-0.26

-0.25

ent

-0.24

ec

-0.24

ela

-0.23

ey

-0.23

enden

-0.23

el

-0.22

ek

-0.22

es

-0.22

POSITIVE LOGITS

thur

0.25

beiten

0.25

beiter

0.24

oon

0.23

hyth

0.21

riors

0.21

aptor

0.21

monic

0.21

thritis

0.21

ctica

0.20

Activations Density 0.117%

words related to architectural terms and structures

No Comments

No Known Activations