INDEX

Explanations

punctuation marks and their surrounding context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

ãģ¾ãģļ

-0.16

anging

-0.15

éĢŁ

-0.14

MLE

-0.14

.generated

-0.14

rics

-0.13

,eg

-0.13

 serialVersionUID

-0.13

assy

-0.13

ãĤ¤ãĥī

-0.13

POSITIVE LOGITS

 similarly

0.44

 Similarly

0.42

Similarly

0.40

 Likewise

0.35

 likewise

0.33

 another

0.32

 similar

0.29

Dit

0.29

 same

0.27

Lik

0.27

Activations Density 0.307%

punctuation marks and their surrounding context

No Comments

No Known Activations

punctuation marks and their surrounding context

No Comments

No Known Activations