INDEX

Explanations

author names and relevant citations in a scholarly context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 9-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L9R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.9.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

ÃŃda

-0.16

pesan

-0.15

áº¯c

-0.15

PRS

-0.14

iasi

-0.14

ZR

-0.14

ANGLES

-0.13

 \↵

-0.13

teri

-0.13

POSITIVE LOGITS

èĤ¡ä»½

0.16

inou

0.15

opia

0.15

åĲĪåĲĮ

0.15

olvency

0.14

 Spells

0.13

 Cout

0.13

velt

0.13

urf

0.13

(&$

0.13

Activations Density 0.007%

author names and relevant citations in a scholarly context

No Comments

No Known Activations