INDEX

Explanations

references to specific programming packages and libraries

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

-0.15

olls

-0.14

iset

-0.14

wcs

-0.13

 outliers

-0.13

olta

-0.13

glomer

-0.13

hub

-0.13

-Level

-0.13

tol

-0.13

POSITIVE LOGITS

oslav

0.15

CEEDED

0.15

uby

0.15

ãģ«ãģĭ

0.14

SubMenu

0.14

uint

0.14

ByExample

0.14

à¸¨à¸£

0.14

<TKey

0.14

ARRANT

0.14

Activations Density 0.047%

references to specific programming packages and libraries

No Comments

No Known Activations