INDEX

Explanations

references to goals and objectives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ESH

-0.16

Globals

-0.16

es

-0.16

uous

-0.15

lak

-0.15

don

-0.15

ese

-0.15

lian

-0.14

esz

-0.14

bubble

-0.14

POSITIVE LOGITS

lessly

0.20

/target

0.19

posts

0.18

/go

0.18

avicon

0.16

Ã³st

0.16

ÙħÙĨØ¯

0.15

ogy

0.15

senal

0.15

inalg

0.15

Activations Density 0.062%

references to goals and objectives

No Comments

No Known Activations