INDEX

Explanations

references to elections and political processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 15-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L15R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.15.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

GetProperty

-0.15

anik

-0.15

ÐµÑĢÐµÐ¶

-0.15

.CLASS

-0.14

oo

-0.14

ces

-0.14

-await

-0.14

hunter

-0.14

omit

-0.14

bre

-0.14

POSITIVE LOGITS

åĳĬ

0.15

 refer

0.15

atest

0.15

icycle

0.15

umat

0.15

 ì¹ĺ

0.14

Fixture

0.14

 Results

0.14

 Disorder

0.14

ATEST

0.14

Activations Density 0.073%

references to elections and political processes

No Comments

No Known Activations