INDEX

Explanations

questions regarding personal preferences and experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

uluk

-0.16

ìĪĻ

-0.15

leston

-0.15

emens

-0.15

Ã¼b

-0.14

Ã©

-0.14

pek

-0.14

REFERENCE

-0.14

antan

-0.13

hlen

-0.13

POSITIVE LOGITS

.nlm

0.17

uy

0.17

 Belly

0.15

uther

0.15

 warn

0.14

afil

0.14

 Cowboy

0.13

iff

0.13

 wides

0.13

Activations Density 0.072%

questions regarding personal preferences and experiences

No Comments

No Known Activations