INDEX

Explanations

language that critiques political figures and parties, particularly in the context of liberal and conservative ideologies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

OKIE

-0.15

Ð½Ð¸ÑĨÑĭ

-0.15

 Blaze

-0.15

ÑħÐ¸

-0.14

ZR

-0.14

elige

-0.14

okie

-0.13

ughters

-0.13

dda

-0.13

 Alto

-0.13

POSITIVE LOGITS

ped

0.31

 pont

0.29

ble

0.28

sp

0.25

par

0.24

reg

0.23

bab

0.22

har

0.22

 trot

0.22

 decl

0.22

Activations Density 0.306%

language that critiques political figures and parties, particularly in the context of liberal and conservative ideologies

No Comments

No Known Activations