INDEX

Explanations

mathematical expressions and integrals in a scientific context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 10-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L10R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.10.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

agen

-0.16

ometrics

-0.15

ouble

-0.14

/colors

-0.14

agem

-0.14

ym

-0.14

irthday

-0.14

ullan

-0.14

adena

-0.14

UTDOWN

-0.13

POSITIVE LOGITS

\views

0.16

imer

0.15

teg

0.15

hair

0.15

\Active

0.14

blr

0.14

cker

0.14

CKER

0.14

bindValue

0.14

abaj

0.13

Activations Density 0.097%

mathematical expressions and integrals in a scientific context

No Comments

No Known Activations