INDEX

Explanations

references to timeframes and durations related to contracts or plans

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

foy

-0.19

fak

-0.16

herits

-0.15

clin

-0.14

Poz

-0.14

vero

-0.14

 Miller

-0.14

agra

-0.14

ÐºÑĢÐµÑĤ

-0.14

_INCLUDED

-0.14

POSITIVE LOGITS

utter

0.16

ulle

0.16

atu

0.15

ilee

0.15

udas

0.15

TEE

0.14

yyn

0.14

¯

0.14

orage

0.14

å¼Ĥ

0.14

Activations Density 0.050%

references to timeframes and durations related to contracts or plans

No Comments

No Known Activations