INDEX

Explanations

mathematical expressions and equations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 4-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L4R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.4.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

#af

-0.16

lasses

-0.16

tega

-0.15

ahl

-0.15

opak

-0.15

Äĩe

-0.14

 Visibility

-0.14

buz

-0.14

eca

-0.14

estone

-0.13

POSITIVE LOGITS

0.15

idence

0.14

 Terr

0.14

Algorithm

0.14

asse

0.14

uche

0.14

ntax

0.13

åľŃ

0.13

Alg

0.13

uania

0.13

Activations Density 0.050%

mathematical expressions and equations

No Comments

No Known Activations