INDEX

Explanations

mathematical symbols and partial derivatives in equations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 23-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L23R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.23.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

ango

-0.16

InstanceState

-0.16

itters

-0.15

ivant

-0.15

_DEFINE

-0.14

çıŃ

-0.14

å·±

-0.14

atcher

-0.14

rimp

-0.13

setMax

-0.13

POSITIVE LOGITS

mu

0.18

Mu

0.17

(mu

0.17

 indices

0.16

Indices

0.16

 Indices

0.16

à¥ľ

0.15

 Alpha

0.15

ab

0.15

eff

0.15

Activations Density 0.030%

mathematical symbols and partial derivatives in equations

No Comments

No Known Activations