INDEX

Explanations

connective phrases that indicate relationships and actions between ideas

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

esium

-0.15

 Pearce

-0.15

ambah

-0.14

ãĤ¤ãĥĪ

-0.14

avage

-0.14

iddle

-0.14

ouve

-0.14

 cryst

-0.14

tÄ±r

-0.13

 maduras

-0.13

POSITIVE LOGITS

/Edit

0.13

vens

0.13

/Search

0.13

 pÅĻitom

0.13

Dll

0.13

 èŃ

0.13

_OM

0.12

ÑĩÐ¸Ð»Ð¸

0.12

åĽłæŃ¤

0.12

DBC

0.12

Activations Density 0.336%

connective phrases that indicate relationships and actions between ideas

No Comments

No Known Activations