INDEX

Explanations

negative sentiments toward common practices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

uxe

-0.19

ç§Ģ

-0.15

hed

-0.14

erre

-0.14

 Charity

-0.14

emy

-0.14

tn

-0.13

 Quit

-0.13

 JpaRepository

-0.13

rito

-0.12

POSITIVE LOGITS

 concept

0.20

 phenomenon

0.20

emann

0.15

coli

0.15

utzer

0.15

 subject

0.15

GRAM

0.14

concept

0.14

 phenomena

0.14

_Lean

0.14

Activations Density 0.220%

negative sentiments toward common practices

No Comments

No Known Activations