INDEX

Explanations

terms related to scientific and technical processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

sko

-0.18

rega

-0.17

Ø¹Ø©

-0.16

ouce

-0.16

atile

-0.16

etten

-0.16

ÅĻe

-0.15

éĤ¦

-0.15

ture

-0.15

ico

-0.14

POSITIVE LOGITS

orph

0.25

iph

0.24

orphism

0.24

ÑĢÐ¸Ð¿

0.23

yn

0.23

opher

0.21

 Crist

0.21

ym

0.21

cript

0.21

 Morph

0.20

Activations Density 0.133%

terms related to scientific and technical processes

No Comments

No Known Activations