INDEX

Explanations

terms related to student and educational contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

rz

-0.16

egr

-0.16

uning

-0.16

uiten

-0.16

abar

-0.15

hana

-0.14

Gir

-0.13

ÑĸÐ¶

-0.13

.childNodes

-0.13

Î®ÏĤ

-0.13

POSITIVE LOGITS

oire

0.16

 Overse

0.15

 baÅŁÄ±nda

0.14

'field

0.14

nton

0.14

Yad

0.14

.WriteByte

0.14

 æ®

0.14

vale

0.14

stead

0.14

Activations Density 0.001%

terms related to student and educational contexts

No Comments

No Known Activations