INDEX

Explanations

jargon and terminology related to specific structured scenarios or cases

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

pie

-0.16

aler

-0.15

rlen

-0.15

enburg

-0.14

 ÐļÑĢÐ°

-0.14

ple

-0.14

isen

-0.14

Et

-0.14

Ð¿Ð¾ÑĢ

-0.14

livÃ©

-0.13

POSITIVE LOGITS

APH

0.15

ç¬Ķ

0.15

raries

0.15

ìĹ¼

0.15

opoulos

0.14

zcze

0.14

 hare

0.14

wa

0.14

/Button

0.14

TokenType

0.13

Activations Density 0.309%

jargon and terminology related to specific structured scenarios or cases

No Comments

No Known Activations