INDEX

Explanations

HTML elements and tags

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

 Hutch

-0.15

umo

-0.15

luet

-0.15

emax

-0.14

plit

-0.14

à¥Īà¤¤

-0.14

yl

-0.14

 Prosper

-0.13

ayscale

-0.13

POSITIVE LOGITS

jev

0.16

id

0.16

tons

0.15

ane

0.15

 class

0.15

 addCriterion

0.15

idian

0.14

 Lazar

0.14

ewan

0.14

 Syndrome

0.14

Activations Density 0.027%

HTML elements and tags

No Comments

No Known Activations