INDEX

Explanations

connections between software and hardware or technological features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

 bÃ¥de

-0.20

 allerdings

-0.18

ocre

-0.18

addtogroup

-0.16

 vÅ¡ak

-0.16

anden

-0.15

 jedoch

-0.15

bable

-0.14

ightly

-0.14

ãģªãģĮ

-0.14

POSITIVE LOGITS

/or

0.90

/OR

0.50

rogen

0.40

/of

0.37

rew

0.34

Ð½Ð°ÑĩÐµ

0.34

rog

0.33

/o

0.32

rea

0.28

erson

0.28

Activations Density 2.009%

connections between software and hardware or technological features

No Comments

No Known Activations

connections between software and hardware or technological features

No Comments

No Known Activations