INDEX

Explanations

references to language learning applications and their features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 28-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L28R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.28.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

ault

-0.16

 retr

-0.16

 Kaiser

-0.15

Ìĥ

-0.15

Ð²Ð°Ð´

-0.14

pu

-0.14

":"'

-0.13

ÅĽnie

-0.13

ÛĢ

-0.13

inputEmail

-0.13

POSITIVE LOGITS

 ConfigureServices

0.16

ugal

0.16

.apps

0.15

ixin

0.15

ulong

0.15

chap

0.15

uj

0.14

fak

0.14

ipple

0.14

uder

0.14

Activations Density 0.037%

references to language learning applications and their features

No Comments

No Known Activations