INDEX

Explanations

references to specific dates and times

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

lace

-0.15

plat

-0.14

à¥Ģà¤ķ

-0.14

OLUTE

-0.14

pl

-0.13

 eskort

-0.13

:frame

-0.13

.isSuccessful

-0.13

POSITIVE LOGITS

oret

0.17

ello

0.14

rna

0.14

 hiatus

0.14

 vibr

0.13

isActive

0.13

vb

0.13

ãģĴ

0.13

strtolower

0.13

 defaultCenter

0.13

Activations Density 0.047%

references to specific dates and times

No Comments

No Known Activations