INDEX

Explanations

proper nouns and names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

Å¡ti

-0.16

osoph

-0.14

issen

-0.14

sah

-0.14

 Reader

-0.14

åħ³

-0.13

reen

-0.13

åİŁ

-0.13

'::

-0.13

 Barry

-0.13

POSITIVE LOGITS

UNCH

0.17

ooled

0.15

endon

0.15

éĢ¸

0.14

Åº

0.14

LOT

0.14

ucher

0.14

_split

0.14

UAGE

0.14

Msp

0.14

Activations Density 0.072%

proper nouns and names

No Comments

No Known Activations