INDEX

Explanations

mentions of media and broadcast references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

akens

-0.16

 Leaf

-0.16

ernel

-0.16

loff

-0.15

opup

-0.15

ctor

-0.15

ctors

-0.14

orney

-0.14

irie

-0.14

TOTYPE

-0.14

POSITIVE LOGITS

air

0.24

 water

0.23

 ropes

0.21

 waters

0.21

 skies

0.20

 wires

0.18

 boards

0.18

_water

0.17

 watermark

0.17

 fences

0.17

Activations Density 0.026%

mentions of media and broadcast references

No Comments

No Known Activations