INDEX

Explanations

Associations with the term "Moscow."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

wares

-0.17

ables

-0.16

-0.15

egers

-0.15

tin

-0.15

ance

-0.15

isable

-0.14

able

-0.13

PLIC

-0.13

POSITIVE LOGITS

quito

0.31

cow

0.25

ambique

0.24

aic

0.20

lems

0.19

quit

0.19

QUIT

0.19

Mos

0.19

lem

0.18

queda

0.18

Activations Density 0.010%

Associations with the term "Moscow."

No Comments

No Known Activations