INDEX

Explanations

geographical locations and river names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

 Hoch

-0.15

idth

-0.15

 soul

-0.14

Ī¬

-0.14

untas

-0.14

 Worm

-0.14

 Priv

-0.14

à¸´à¸Ķ

-0.14

clipse

-0.14

 Scal

-0.14

POSITIVE LOGITS

pur

0.31

pur

0.23

Pur

0.21

PUR

0.20

abad

0.20

apur

0.20

ipur

0.20

 gram

0.19

 Gram

0.19

pora

0.18

Activations Density 0.166%

geographical locations and river names

No Comments

No Known Activations