INDEX

Explanations

terms related to "spot" or "spotting" 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 @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

how

-0.19

utom

-0.19

al

-0.18

hall

-0.17

hma

-0.17

have

-0.16

bsolute

-0.16

esa

-0.16

hape

-0.15

ÑģÑĮ

-0.15

POSITIVE LOGITS

ting

0.39

ter

0.34

lights

0.33

tery

0.23

aneous

0.23

tern

0.21

TER

0.20

tering

0.19

tingham

0.19

tement

0.18

Activations Density 0.029%

terms related to "spot" or "spotting" in various contexts

No Comments

No Known Activations