INDEX

Explanations

mathematical symbols and structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 19-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L19R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.19.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

ents

-0.16

mob

-0.15

Vor

-0.15

ãĥ¼ãĥª

-0.14

lotte

-0.14

à¸¸à¸ģ

-0.14

zell

-0.14

stroy

-0.14

reatest

-0.14

ëĿ½

-0.14

POSITIVE LOGITS

 Randall

0.19

 dark

0.18

SM

0.17

 Dark

0.17

 collider

0.16

MSS

0.16

 scenarios

0.16

Dark

0.16

mrb

0.16

dark

0.15

Activations Density 0.010%

mathematical symbols and structures

No Comments

No Known Activations