INDEX

Explanations

numbers and numerical representations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

-0.14

 beden

-0.14

ÙģØ§ÙĤ

-0.14

arios

-0.14

emax

-0.13

zap

-0.13

 Super

-0.13

ZA

-0.13

 Desk

-0.13

POSITIVE LOGITS

onis

0.17

ccione

0.16

hdl

0.15

ÙĦØ¹

0.15

å¡ļ

0.15

pository

0.15

 Fallen

0.14

urdu

0.14

adies

0.14

ëł¹

0.14

Activations Density 0.000%

numbers and numerical representations

No Comments

No Known Activations