INDEX

Explanations

elements related to construction and architectural features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

gene

-0.15

gency

-0.15

PID

-0.15

 Shack

-0.14

 Paper

-0.14

ãģıãĤĵ

-0.14

icina

-0.13

 paper

-0.13

_paper

-0.13

hart

-0.13

POSITIVE LOGITS

 rail

0.42

 Rail

0.39

rail

0.35

Rail

0.32

 railing

0.31

 rails

0.30

rails

0.28

bal

0.28

 Rails

0.26

 guard

0.24

Activations Density 0.066%

elements related to construction and architectural features

No Comments

No Known Activations