INDEX

Explanations

references to settings and configuration options in software

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

ycop

-0.15

hev

-0.14

akit

-0.14

lÃ½

-0.14

ATAB

-0.14

åĶ

-0.13

 Stevens

-0.13

ortal

-0.13

rig

-0.13

atab

-0.13

POSITIVE LOGITS

ardown

0.15

$LANG

0.14

doz

0.14

Ð¼Ð°Ñħ

0.14

allee

0.14

edit

0.13

 pathMatch

0.13

á»¯a

0.13

erox

0.13

.AppSettings

0.13

Activations Density 0.076%

references to settings and configuration options in software

No Comments

No Known Activations