INDEX

Explanations

references to symbolic concepts and representations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

est

-0.17

-0.16

rott

-0.15

ÑĢÐ¸Ð³

-0.15

rens

-0.15

ully

-0.14

ì¸

-0.14

ughter

-0.14

atra

-0.14

ellig

-0.14

POSITIVE LOGITS

chai

0.15

oenix

0.15

minent

0.15

urat

0.15

HideInInspector

0.15

mith

0.15

phants

0.14

Kee

0.14

dden

0.14

 ÑģÐ¾Ð±Ð¾Ð¹

0.14

Activations Density 0.021%

references to symbolic concepts and representations

No Comments

No Known Activations