INDEX

Explanations

terms related to documentation and record-keeping

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

dry

-0.16

per

-0.15

gest

-0.15

idor

-0.15

apon

-0.15

 ÙĨØ§ÙħÙĩ

-0.15

-strokes

-0.14

otros

-0.14

uu

-0.14

rol

-0.14

POSITIVE LOGITS

-breaking

0.20

edly

0.17

agli

0.16

ixe

0.15

heim

0.15

anye

0.15

iciel

0.14

RTC

0.14

ffi

0.14

ukan

0.14

Activations Density 0.034%

terms related to documentation and record-keeping

No Comments

No Known Activations