INDEX

Explanations

numerical information and dates

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ewire

-0.17

lingen

-0.15

::::::

-0.15

ickey

-0.15

.cf

-0.15

enden

-0.14

emoc

-0.14

wow

-0.14

ureau

-0.13

amerate

-0.13

POSITIVE LOGITS

th

0.26

nd

0.18

st

0.18

rd

0.18

 third

0.17

_nth

0.17

 second

0.16

 fourth

0.16

ly

0.15

ith

0.15

Activations Density 0.025%

numerical information and dates

No Comments

No Known Activations