INDEX

Explanations

mathematical terms and symbols related to limits and functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

.dp

-0.16

aticon

-0.15

icode

-0.14

Î½Î±Î½

-0.14

é§

-0.14

ombine

-0.14

.Experimental

-0.14

roys

-0.13

umatic

-0.13

iropr

-0.13

POSITIVE LOGITS

 skal

0.21

 line

0.21

 Matrix

0.20

 rationale

0.20

 reel

0.19

 Operator

0.18

 Norm

0.18

 indu

0.18

 Tensor

0.17

Pot

0.17

Activations Density 0.008%

mathematical terms and symbols related to limits and functions

No Comments

No Known Activations