INDEX

Explanations

references to students and their actions or status in an academic or educational context

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

Ð¾Ð²ÐµÑĢ

-0.17

aggio

-0.17

ersonic

-0.16

dden

-0.15

ÑĩÐ°ÑĤ

-0.14

emey

-0.14

llum

-0.14

CAPE

-0.14

Ð½Ð°Ð²

-0.14

uros

-0.14

POSITIVE LOGITS

Ð½Ð°ÑĩÐµ

0.16

mina

0.14

ound

0.14

ä½

0.14

 balance

0.14

acha

0.14

 Parkway

0.14

çİ²

0.13

aco

0.13

Activations Density 0.790%

references to students and their actions or status in an academic or educational context

No Comments

No Known Activations