INDEX

Explanations

references to various aspects of education and training

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

irates

-0.17

 Ð²Ð¼ÐµÑģÑĤ

-0.16

imat

-0.15

instead

-0.15

duk

-0.15

 instead

-0.15

ank

-0.15

 fist

-0.14

;element

-0.14

ifter

-0.14

POSITIVE LOGITS

 ÙħØ¨Ø§Ø´

0.20

 confines

0.20

 alone

0.20

alone

0.19

 altogether

0.18

 Alone

0.17

 anymore

0.17

 bounds

0.15

 scope

0.15

ntity

0.15

Activations Density 0.087%

references to various aspects of education and training

No Comments

No Known Activations