INDEX

Explanations

equal signs in a structured format, likely indicating attributes or properties within code or markup

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

/or

-0.20

/OR

-0.16

ekil

-0.16

agher

-0.14

egend

-0.14

ekim

-0.14

/o

-0.13

bour

-0.13

phanumeric

-0.13

itals

-0.13

POSITIVE LOGITS

0.27

odore

0.17

suite

0.17

sut

0.16

ed

0.16

sburg

0.16

andre

0.15

sav

0.15

eenth

0.15

enze

0.15

Activations Density 0.085%

equal signs in a structured format, likely indicating attributes or properties within code or markup

No Comments

No Known Activations