INDEX

Explanations

references to political decisions and government actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

ãĥ³ãĥĳ

-0.17

OKIE

-0.15

ECTOR

-0.15

gz

-0.15

Drv

-0.15

 metab

-0.15

 Maul

-0.14

istique

-0.14

 stap

-0.14

posix

-0.14

POSITIVE LOGITS

 Popular

0.20

Evo

0.20

Dil

0.19

 Rousse

0.19

Kir

0.19

Fuj

0.18

 left

0.18

PT

0.18

kir

0.17

Bol

0.17

Activations Density 0.039%

references to political decisions and government actions

No Comments

No Known Activations