INDEX

Explanations

references to participation and opportunities in events or organizations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

 Hammond

-0.15

 thÃ´i

-0.15

ceipt

-0.14

 Ð¿ÐµÑĢÐµÐ´Ð°

-0.14

otec

-0.14

zin

-0.14

 Kramer

-0.13

esh

-0.13

ì°¨

-0.13

NP

-0.13

POSITIVE LOGITS

aga

0.17

@student

0.15

ãĥ³ãĤ¹

0.15

ilia

0.15

apia

0.14

 opportunity

0.14

Ð¾Ð´ÐµÑĢÐ¶

0.14

awah

0.14

agos

0.14

uhan

0.14

Activations Density 0.259%

references to participation and opportunities in events or organizations

No Comments

No Known Activations