INDEX

Explanations

references to specific dates or years

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

 ÐļÐ¾Ð´

-0.15

enko

-0.14

à¸ķà¸£à¸ĩ

-0.14

 lesb

-0.14

pie

-0.14

 exact

-0.14

ocode

-0.14

oad

-0.13

iya

-0.13

POSITIVE LOGITS

ahren

0.16

itti

0.16

umph

0.16

hton

0.15

osis

0.15

Deque

0.14

PathParam

0.14

CTS

0.14

bage

0.14

amework

0.14

Activations Density 0.053%

references to specific dates or years

No Comments

No Known Activations