INDEX

Explanations

terms and settings related to software configuration and programming languages

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

ÐµÐºÑĤÐ¸Ð²

-0.15

imers

-0.15

borg

-0.14

acher

-0.14

 breath

-0.14

ÅĻi

-0.14

 mess

-0.14

eral

-0.13

archive

-0.13

att

-0.13

POSITIVE LOGITS

marsh

0.15

ritel

0.15

.IContainer

0.15

å°ĺ

0.15

etration

0.14

iaux

0.14

HEET

0.14

 strSQL

0.14

sett

0.14

summ

0.14

Activations Density 0.000%

terms and settings related to software configuration and programming languages

No Comments

No Known Activations