INDEX

Explanations

specific numerical and categorical data related to admissions and statistics

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

 latter

-0.15

pawn

-0.14

éļ

-0.14

Ñĺ

-0.13

xious

-0.13

 king

-0.13

 Ø³Ùħ

-0.13

 ìĿ´ë¥¼

-0.13

ORT

-0.13

InSection

-0.13

POSITIVE LOGITS

isor

0.15

Spo

0.14

ifest

0.14

 Newman

0.14

\modules

0.14

esture

0.14

 coats

0.14

coat

0.13

estroy

0.13

ÙĤØ©

0.13

Activations Density 0.098%

specific numerical and categorical data related to admissions and statistics

No Comments

No Known Activations