INDEX

Explanations

multi-part phrases and actions related to online content management or interaction

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

-treated

-0.15

-0.14

 Rescue

-0.14

 Netz

-0.14

 crises

-0.13

Ð°ÑĢÑĩ

-0.13

 Randolph

-0.13

 transient

-0.13

 rescue

-0.13

 bare

-0.12

POSITIVE LOGITS

Ahead

0.16

 prep

0.16

éĢ

0.16

byss

0.15

Î¿ÏįÏĤ

0.15

 preparations

0.15

linky

0.15

 ante

0.15

ãĤ¹ãĤ¿ãĥ¼

0.14

 preparation

0.14

Activations Density 0.002%

multi-part phrases and actions related to online content management or interaction

No Comments

No Known Activations