INDEX

Explanations

measurements and calculations related to quantity and conversion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

MATRIX

-0.14

 máº·t

-0.14

 retro

-0.14

inson

-0.14

ello

-0.14

 shrink

-0.14

 Retro

-0.13

 viol

-0.13

ÄĽl

-0.13

acom

-0.13

POSITIVE LOGITS

 units

0.23

 Units

0.21

SI

0.20

 unit

0.20

:convert

0.20

 conversions

0.19

units

0.19

 conversion

0.19

Units

0.18

åįķä½į

0.18

Activations Density 0.049%

measurements and calculations related to quantity and conversion

No Comments

No Known Activations