INDEX

Explanations

references to traditional concepts, practices, or items across various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

arel

-0.16

ogl

-0.15

indr

-0.14

bras

-0.13

thing

-0.13

ings

-0.13

mented

-0.13

sburg

-0.13

.joda

-0.13

/he

-0.13

POSITIVE LOGITS

ists

0.36

ist

0.31

ISTS

0.24

ism

0.24

itionally

0.23

/current

0.22

isti

0.21

ista

0.21

-looking

0.21

istic

0.20

Activations Density 0.029%

references to traditional concepts, practices, or items across various contexts

No Comments

No Known Activations