INDEX

Explanations

phrases related to fees or charges

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 17-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L17R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.17.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

ardo

-0.17

emann

-0.17

 Ð·Ð°ÑģÑĤ

-0.16

ertino

-0.14

¢åįķ

-0.14

onta

-0.14

çŃĶæ¡Ī

-0.14

æµ

-0.14

olen

-0.14

 Wein

-0.14

POSITIVE LOGITS

0.16

ruta

0.16

hid

0.16

à¸´à¸§

0.15

agal

0.15

 Conce

0.15

0.14

dna

0.14

 truth

0.14

ume

0.14

Activations Density 0.000%

phrases related to fees or charges

No Comments

No Known Activations