INDEX

Explanations

mathematical notations and structures used in advanced theoretical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

avou

-0.17

Wa

-0.17

 Leisure

-0.16

ogn

-0.15

lernen

-0.15

ake

-0.15

ìĸ¸

-0.15

ãĤĵãģ©

-0.15

raig

-0.14

avÄĽ

-0.14

POSITIVE LOGITS

sob

0.21

Bes

0.17

 rough

0.17

sob

0.16

 overlapping

0.16

elier

0.15

tae

0.15

Sob

0.15

 smooth

0.15

Activations Density 0.058%

mathematical notations and structures used in advanced theoretical contexts

No Comments

No Known Activations