INDEX

Explanations

terms related to admission or entry processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

ãĥ³ãĥĶ

-0.16

otts

-0.15

rani

-0.15

ìļ±

-0.14

bst

-0.14

bie

-0.14

onestly

-0.14

å°¼äºļ

-0.14

Î¼Î±Î¹

-0.14

amp

-0.14

POSITIVE LOGITS

à¸°

0.15

Ģë¡ľ

0.14

ric

0.14

ä¸ĢåĮº

0.14

ç¥ĸ

0.13

Ø¯ÙĩØ§ÛĮ

0.13

 Benny

0.13

>tag

0.13

ÅĻeh

0.13

iesz

0.13

Activations Density 0.004%

terms related to admission or entry processes

No Comments

No Known Activations