INDEX

Explanations

discussions related to political and social power dynamics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

cheng

-0.13

ä½³

-0.13

ä¼ĺ

-0.13

 paci

-0.13

velopment

-0.12

ux

-0.12

 Registrar

-0.12

Ð¾Ð¶Ð´ÐµÐ½Ð¸Ñı

-0.12

ç³ĸ

-0.12

 láº¡c

-0.12

POSITIVE LOGITS

 Conspiracy

0.28

 conspiracy

0.27

 Bilder

0.25

 Truth

0.25

UFO

0.24

MSM

0.24

 conspir

0.24

 truth

0.24

 Roths

0.23

Activations Density 0.479%

discussions related to political and social power dynamics

No Comments

No Known Activations