INDEX

Explanations

social media and online interaction markers

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

OLUMN

-0.16

etto

-0.15

ession

-0.15

alez

-0.15

burgh

-0.15

yat

-0.14

_Tis

-0.14

Å¾el

-0.14

ÑĮÐºÐ¾

-0.14

lrt

-0.14

POSITIVE LOGITS

azon

0.17

 mint

0.15

uru

0.15

athi

0.15

atha

0.14

Yaz

0.14

ennes

0.14

aed

0.13

 hint

0.13

ute

0.13

Activations Density 0.009%

social media and online interaction markers

No Comments

No Known Activations