INDEX

Explanations

numerical values and references to mathematical concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

äºľ

-0.15

Inlining

-0.15

iten

-0.15

 Speech

-0.14

 maximum

-0.14

veis

-0.14

ochen

-0.14

speech

-0.13

 Dexter

-0.13

filt

-0.13

POSITIVE LOGITS

 Math

0.27

 math

0.27

math

0.26

 mathematics

0.26

 Mathematics

0.25

Math

0.24

 Addition

0.24

 problem

0.24

"math

0.24

 Ø§ÙĦØ±ÙĬØ§Ø¶

0.24

Activations Density 0.180%

numerical values and references to mathematical concepts

No Comments

No Known Activations