INDEX

Explanations

references to intelligence or intelligent beings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

Ð¾ÑĪ

-0.16

nell

-0.16

gaard

-0.15

Evt

-0.15

à¸£à¸ĩà¹Ģà¸£

-0.14

ÌĤ

-0.14

Ø§ÛĮØ±

-0.14

istrovstvÃŃ

-0.14

CLUDING

-0.14

Ð¾Ð¾Ð±ÑĢÐ°Ð·

-0.14

POSITIVE LOGITS

0.16

zeich

0.15

esse

0.15

esch

0.15

ruh

0.15

rage

0.14

vg

0.14

rag

0.14

ten

0.14

Activations Density 0.016%

references to intelligence or intelligent beings

No Comments

No Known Activations