INDEX

Explanations

negative expressions or sentiments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

arer

-0.17

inki

-0.15

LEM

-0.14

redo

-0.14

Nez

-0.14

.require

-0.14

akers

-0.14

opak

-0.13

ryo

-0.13

abwe

-0.13

POSITIVE LOGITS

å¼ı

0.15

ejs

0.15

iman

0.15

imson

0.15

 Sahara

0.14

 fools

0.14

-uppercase

0.13

Mec

0.13

&view

0.13

Activations Density 0.042%

negative expressions or sentiments

No Comments

No Known Activations