INDEX

Explanations

programming or markup language syntax elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

 Vest

-0.18

elli

-0.15

oun

-0.14

 witness

-0.14

oron

-0.14

enn

-0.13

ission

-0.13

 ÙģØ§Ø±

-0.13

 witnessing

-0.13

ils

-0.13

POSITIVE LOGITS

loven

0.16

ldr

0.15

¶ģ

0.14

ennai

0.14

ronym

0.14

ovsky

0.14

CEED

0.14

vÅ¯li

0.14

ynchronously

0.14

 tomu

0.14

Activations Density 0.033%

programming or markup language syntax elements

No Comments

No Known Activations