INDEX

Explanations

references to dogs and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

edImage

-0.21

eton

-0.17

edException

-0.17

arios

-0.17

anism

-0.15

steen

-0.15

åı·

-0.15

Ã³r

-0.15

rious

-0.14

oise

-0.14

POSITIVE LOGITS

gy

0.29

ged

0.28

gie

0.28

ging

0.23

gett

0.22

fight

0.21

ma

0.20

ger

0.20

/cat

0.20

go

0.18

Activations Density 0.018%

references to dogs and related terms

No Comments

No Known Activations