INDEX

Explanations

phrases indicating organizational structure or components of a strategy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

noch

-0.17

awy

-0.15

_shapes

-0.14

SED

-0.14

.generated

-0.14

vens

-0.14

shima

-0.14

ope

-0.14

awi

-0.13

ullan

-0.13

POSITIVE LOGITS

 effort

0.24

 efforts

0.21

 ongoing

0.20

ongo

0.19

 broader

0.17

 series

0.16

 normal

0.16

 duties

0.16

mat

0.15

 duty

0.14

Activations Density 0.047%

phrases indicating organizational structure or components of a strategy

No Comments

No Known Activations