INDEX

Explanations

references to design and its various forms or expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

ality

-0.16

ht

-0.16

ies

-0.15

als

-0.15

iel

-0.14

exp

-0.14

iers

-0.14

 GÃ¼l

-0.14

InView

-0.14

bral

-0.13

POSITIVE LOGITS

ated

0.18

ations

0.18

ATED

0.18

atedRoute

0.17

ating

0.17

ATING

0.17

çĲĨ

0.16

/design

0.16

AGMA

0.16

ators

0.16

Activations Density 0.023%

references to design and its various forms or expressions

No Comments

No Known Activations