INDEX

Explanations

terms related to different types of conditions or diseases

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

ed

-0.25

es

-0.22

al

-0.22

ita

-0.21

itel

-0.19

ti

-0.19

edn

-0.18

it

-0.18

ey

-0.18

ky

-0.18

POSITIVE LOGITS

omial

0.24

cola

0.24

abox

0.23

coln

0.21

nesota

0.21

ews

0.21

fty

0.20

ners

0.20

shaw

0.20

arily

0.20

Activations Density 0.134%

terms related to different types of conditions or diseases

No Comments

No Known Activations