INDEX

Explanations

terms related to educational institutions and companies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

uguay

-0.15

elves

-0.14

artner

-0.14

à¸Ļà¸²à¸ĩ

-0.13

lider

-0.13

usz

-0.13

istas

-0.13

anta

-0.13

igkeit

-0.13

ensa

-0.13

POSITIVE LOGITS

Î¶Î±

0.15

tet

0.14

Éµ

0.14

terra

0.13

MESS

0.13

oruÄį

0.13

 ÑĢÑĥÐºÐ°Ñħ

0.13

rani

0.13

Campo

0.13

pseudo

0.13

Activations Density 0.141%

terms related to educational institutions and companies

No Comments

No Known Activations