INDEX

Explanations

references to player roles and team structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 27-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L27R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.27.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

-0.17

 Phen

-0.16

 phenomenon

-0.15

 escorte

-0.15

ÐĴÑĤ

-0.14

ØªÙĦ

-0.14

longleftrightarrow

-0.14

amat

-0.13

borg

-0.13

POSITIVE LOGITS

 side

0.33

 squad

0.31

 starting

0.27

 Starting

0.26

 Side

0.24

starting

0.24

 Squad

0.23

 lineup

0.23

sq

0.23

side

0.22

Activations Density 0.039%

references to player roles and team structures

No Comments

No Known Activations