INDEX

Explanations

programming-related terms and concepts involving data structures and numerical computations

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

[][]

-0.22

 [][]

-0.20

[[]

-0.17

[][

-0.17

loys

-0.16

[['

-0.15

[:,:,

-0.15

[:,:

-0.15

iazza

-0.15

thood

-0.15

POSITIVE LOGITS

 array

0.20

 sequence

0.19

NSArray

0.18

 vector

0.18

æķ°ç»Ħ

0.17

 Redemption

0.16

Sequence

0.16

 Sequence

0.16

ToArray

0.16

ivec

0.16

Activations Density 0.176%

programming-related terms and concepts involving data structures and numerical computations

No Comments

No Known Activations