INDEX

Explanations

mentions of the syllable "au" and its variations within the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

sta

-0.18

ta

-0.17

als

-0.16

Ø¹

-0.16

ÙĦ

-0.15

leton

-0.15

les

-0.15

EI

-0.15

gui

-0.15

à¹īà¸²à¸§

-0.15

POSITIVE LOGITS

ropa

0.21

ãĤ¢ãĥ¼

0.17

ROL

0.17

wk

0.17

jÃŃm

0.17

Ð½Ð°ÑĢÐ¾Ð´

0.16

ÃŁer

0.16

rop

0.16

wf

0.16

Ã«r

0.15

Activations Density 0.025%

mentions of the syllable "au" and its variations within the text

No Comments

No Known Activations