INDEX

Explanations

symbols and code elements related to programming or scripting

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

hani

-0.17

usch

-0.16

ussia

-0.15

 Blick

-0.14

zug

-0.14

zim

-0.14

Î²Î¿Î»

-0.13

ipple

-0.13

ges

-0.13

ius

-0.13

POSITIVE LOGITS

ufs

0.18

ÅĻÃŃ

0.14

.scalablytyped

0.14

 Banc

0.14

URRED

0.14

UREMENT

0.13

otten

0.13

alker

0.13

myp

0.13

Activations Density 0.085%

symbols and code elements related to programming or scripting

No Comments

No Known Activations