INDEX

Explanations

references to specific films or cinema styles

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ness

-0.32

so

-0.32

ìĿĦ

-0.27

ship

-0.27

ne

-0.27

nya

-0.27

ri

-0.27

land

-0.26

self

-0.24

set

-0.23

POSITIVE LOGITS

urope

0.21

ighborhood

0.16

lected

0.16

ourcem

0.16

iros

0.16

ighbors

0.15

ems

0.15

vents

0.15

pond

0.15

iro

0.15

Activations Density 0.556%

references to specific films or cinema styles

No Comments

No Known Activations