INDEX

Explanations

names and terms associated with specific political figures or entities

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

itage

-0.17

åĽŃ

-0.15

untas

-0.15

uxt

-0.15

âĶ´

-0.15

beg

-0.15

åľĴ

-0.15

ÙĦØ¨

-0.14

hang

-0.14

 Sutton

-0.14

POSITIVE LOGITS

ech

0.20

kaar

0.19

ECH

0.15

itech

0.14

çŃĭ

0.14

 Bert

0.14

 Bourbon

0.14

rottle

0.14

scan

0.14

etta

0.14

Activations Density 0.010%

names and terms associated with specific political figures or entities

No Comments

No Known Activations