INDEX

Explanations

conditional and probabilistic expressions related to uncertainty or possibilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

entine

-0.16

increment

-0.15

Ã²i

-0.14

 åı¤

-0.14

isman

-0.14

åŀĤ

-0.14

iod

-0.14

edis

-0.14

Ø¨Ø§ÙĨ

-0.13

 Heritage

-0.13

POSITIVE LOGITS

ippo

0.15

 èī¯

0.15

.exc

0.14

ortic

0.14

Advisor

0.14

KP

0.13

uteur

0.13

 Blackhawks

0.13

claim

0.13

Activations Density 0.865%

conditional and probabilistic expressions related to uncertainty or possibilities

No Comments

No Known Activations