INDEX

Explanations

mentions of political leaders and officials, particularly in the context of global events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

vale

-0.17

miss

-0.17

 Boss

-0.14

akit

-0.14

Opera

-0.14

utom

-0.14

ubat

-0.13

cab

-0.13

OMEM

-0.13

 Situation

-0.13

POSITIVE LOGITS

Joi

0.16

ween

0.15

 Nets

0.14

zas

0.14

 Merk

0.14

 srand

0.13

 ÑģÐ¾Ð·

0.13

iker

0.13

 FOREIGN

0.13

chner

0.13

Activations Density 0.041%

mentions of political leaders and officials, particularly in the context of global events

No Comments

No Known Activations