INDEX

Explanations

actions and movements occurring in 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 @ 29-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L29R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.29.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

 upside

-0.19

 outright

-0.14

cki

-0.14

 flatt

-0.13

icina

-0.13

aris

-0.13

ÑģÐ¿ÑĸÐ»ÑĮ

-0.13

near

-0.13

uri

-0.13

POSITIVE LOGITS

 forward

0.47

 Forward

0.36

 onto

0.35

 past

0.34

 FORWARD

0.34

 into

0.33

forward

0.32

_forward

0.32

onto

0.31

Forward

0.31

Activations Density 0.727%

actions and movements occurring in various contexts

No Comments

No Known Activations