INDEX

Explanations

quotation marks and punctuation related to dialogue

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

duk

-0.17

çŃĸ

-0.14

ergus

-0.14

untime

-0.14

etik

-0.14

:end

-0.13

ëħ

-0.13

aptic

-0.13

ä¸įäºĨ

-0.13

POSITIVE LOGITS

 salad

0.15

æ£Ĵ

0.15

remium

0.15

orris

0.14

ittings

0.14

 servisi

0.13

Ð¾ÑģÐ¾Ð±

0.13

rah

0.13

anghai

0.13

 Salad

0.13

Activations Density 0.126%

quotation marks and punctuation related to dialogue

No Comments

No Known Activations