INDEX

Explanations

mathematical notations and symbols associated with graph theory and probability distributions

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

ward

-0.18

essel

-0.16

nell

-0.14

ults

-0.14

 BÄĽ

-0.13

ãĥĨãĥ«

-0.13

.hh

-0.13

Mapper

-0.13

 Ukra

-0.13

pson

-0.13

POSITIVE LOGITS

ÐºÑģ

0.15

¦æĥħ

0.14

avar

0.14

Ð°Ð½Ð¸ÑĨ

0.13

Ã¤d

0.13

_OID

0.13

itÃ¤

0.13

afone

0.13

arious

0.13

 Ordering

0.13

Activations Density 0.084%

mathematical notations and symbols associated with graph theory and probability distributions

No Comments

No Known Activations