INDEX

Explanations

references to historical or geographical entities, particularly relating to places or figures from ancient times

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

Xu

-0.17

 Jonas

-0.17

Ð¾ÐºÑĢÐ°ÑĤÐ¸

-0.16

asco

-0.16

ÐµÐ¼Ð°ÑĤÐ¸

-0.15

xu

-0.15

inski

-0.14

 Buna

-0.14

ickey

-0.14

 Narrow

-0.14

POSITIVE LOGITS

aria

0.49

ria

0.46

oria

0.45

onia

0.44

ania

0.44

lia

0.43

nia

0.42

elia

0.42

RIA

0.42

 Maria

0.42

Activations Density 0.214%

references to historical or geographical entities, particularly relating to places or figures from ancient times

No Comments

No Known Activations