INDEX

Explanations

phrases related to locations and events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

apas

-0.17

utom

-0.15

aler

-0.15

ynos

-0.14

 mark

-0.14

elligence

-0.14

udas

-0.14

Gam

-0.14

abox

-0.13

Ab

-0.13

POSITIVE LOGITS

onse

0.15

mer

0.15

çĻ

0.14

kas

0.14

_linked

0.14

uesta

0.14

ingle

0.14

obi

0.14

opolitan

0.14

atta

0.14

Activations Density 0.030%

phrases related to locations and events

No Comments

No Known Activations