INDEX

Explanations

references to recent releases or updates in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

ertools

-0.16

rog

-0.15

ammen

-0.15

Ð´Ð°ÑĤ

-0.14

stad

-0.14

ÑģÑĤÑĢÐ°

-0.14

.Quad

-0.13

á»©t

-0.13

Ð°ÑĢÐ°Ð½

-0.13

ationToken

-0.13

POSITIVE LOGITS

 batch

0.23

/current

0.23

 additions

0.20

/latest

0.20

 addition

0.18

batch

0.18

est

0.18

 iteration

0.18

0.17

 Addition

0.17

Activations Density 0.017%

references to recent releases or updates in various contexts

No Comments

No Known Activations