INDEX

Explanations

mentions of JavaScript or related code elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

TER

-0.17

bot

-0.16

ingham

-0.16

REP

-0.16

osemite

-0.15

ignKey

-0.15

Bot

-0.15

Bot

-0.15

umen

-0.14

esa

-0.14

POSITIVE LOGITS

/software

0.16

urch

0.15

rena

0.14

errer

0.14

baar

0.14

RN

0.14

alk

0.13

\grid

0.13

zept

0.13

 Initialized

0.13

Activations Density 0.027%

mentions of JavaScript or related code elements

No Comments

No Known Activations