INDEX

Explanations

specific punctuation marks and symbols commonly used in programming or data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

iesz

-0.17

QueryParam

-0.16

amburg

-0.15

ameda

-0.15

bart

-0.15

ìĸ¸

-0.15

IES

-0.15

afone

-0.15

Nex

-0.15

usic

-0.15

POSITIVE LOGITS

Ø²Ùĩ

0.14

 carrier

0.14

 perch

0.14

 Carrie

0.14

andle

0.14

ingers

0.13

 doubt

0.13

hell

0.13

ngx

0.13

Dil

0.13

Activations Density 0.004%

specific punctuation marks and symbols commonly used in programming or data structures

No Comments

No Known Activations