INDEX

Explanations

references to political parties and their affiliations

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

ì¸ł

-0.15

 Melania

-0.14

 Diary

-0.13

 Oval

-0.13

á»ĭp

-0.13

WT

-0.13

ãĥŃãĥ¼

-0.13

antor

-0.13

.HttpContext

-0.13

CNN

-0.13

POSITIVE LOGITS

 party

0.40

 Party

0.36

 parties

0.35

 Alliance

0.33

party

0.32

 Parties

0.31

Party

0.31

 Movement

0.30

 Progressive

0.29

-party

0.29

Activations Density 0.066%

references to political parties and their affiliations

No Comments

No Known Activations