INDEX

Explanations

specifications or attributes in a structured format, likely related to programming or data representation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ersh

-0.19

eza

-0.15

ree

-0.15

ervo

-0.15

LARI

-0.15

gart

-0.14

bps

-0.14

NSNotification

-0.14

rotch

-0.14

ÐºÑĥÑģ

-0.14

POSITIVE LOGITS

 Stub

0.16

 Henderson

0.14

obre

0.14

ONDON

0.14

ASM

0.14

ient

0.13

 control

0.13

 inst

0.13

onde

0.13

Ä±r

0.13

Activations Density 0.030%

specifications or attributes in a structured format, likely related to programming or data representation

No Comments

No Known Activations