INDEX

Explanations

phrases related to making correct or optimal decisions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

ORIZONTAL

-0.15

rk

-0.15

uhe

-0.14

ricks

-0.14

kee

-0.13

rz

-0.13

ecess

-0.13

icap

-0.13

 Bald

-0.13

Î¹ÏĥÏĦÎ¿

-0.13

POSITIVE LOGITS

fully

0.17

arch

0.16

¦

0.15

urga

0.15

zeitig

0.15

orch

0.14

-hand

0.14

 Millenn

0.14

arth

0.14

Ub

0.14

Activations Density 0.034%

phrases related to making correct or optimal decisions

No Comments

No Known Activations