INDEX

Explanations

technical terms and programming language syntax

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

 altura

-0.14

 Spinner

-0.14

 Spin

-0.14

FY

-0.14

-0.13

å»

-0.13

Gow

-0.13

soo

-0.13

eners

-0.13

¦

-0.13

POSITIVE LOGITS

zek

0.17

pok

0.16

isa

0.15

ëĵ±ë¡Ŀ

0.15

onte

0.15

bron

0.15

pent

0.15

ayload

0.15

hev

0.14

 hÆ¡i

0.14

Activations Density 0.200%

technical terms and programming language syntax

No Comments

No Known Activations