INDEX

Explanations

references to additional benefits or bonuses

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

go

-0.16

put

-0.16

soever

-0.16

apiro

-0.16

atsapp

-0.15

istle

-0.15

 Further

-0.15

azo

-0.15

PUR

-0.15

ableObject

-0.15

POSITIVE LOGITS

ordinary

0.44

ord

0.35

-large

0.34

ORD

0.33

ordin

0.32

-cur

0.28

ordinal

0.27

-long

0.26

ocular

0.26

-special

0.26

Activations Density 0.021%

references to additional benefits or bonuses

No Comments

No Known Activations