INDEX

Explanations

mathematical expressions and patterns involving logical operations and comparisons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

arak

-0.15

stav

-0.14

nap

-0.14

 rollers

-0.14

idon

-0.14

testimonial

-0.14

inne

-0.14

ÏĨÎ¹

-0.14

LPARAM

-0.14

lesc

-0.14

POSITIVE LOGITS

otto

0.17

.timedelta

0.16

ODEV

0.15

oui

0.15

amps

0.14

)/

0.14

 Electoral

0.14

vil

0.14

áº§n

0.13

imer

0.13

Activations Density 0.188%

mathematical expressions and patterns involving logical operations and comparisons

No Comments

No Known Activations