INDEX

Explanations

phrases indicating preparation or readiness for an upcoming event or action

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

olet

-0.15

 quant

-0.14

ÏģÏİ

-0.14

à¸µà¸¢à¸Ķ

-0.14

Convention

-0.14

 Duty

-0.13

ritos

-0.13

ERA

-0.13

calar

-0.13

ç®±

-0.13

POSITIVE LOGITS

orton

0.15

mdl

0.15

 Ð½ÐµÑĢ

0.14

omo

0.14

insic

0.14

roperty

0.14

abbit

0.14

iÅ¡tÄĽ

0.13

Activations Density 0.005%

phrases indicating preparation or readiness for an upcoming event or action

No Comments

No Known Activations