INDEX

Explanations

references to tribes or tribal communities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

/goto

-0.17

lund

-0.16

aurant

-0.15

ieme

-0.15

,proto

-0.15

XR

-0.14

 Fritz

-0.14

ugin

-0.14

acement

-0.14

eu

-0.14

POSITIVE LOGITS

PIO

0.15

apa

0.15

ocal

0.14

Injector

0.14

wagon

0.14

Separator

0.14

je

0.14

ç¡

0.13

etting

0.13

Ø±ÛĮÙħ

0.13

Activations Density 0.005%

references to tribes or tribal communities

No Comments

No Known Activations