INDEX

Explanations

phrases that indicate opinions or commentary on player performance and team dynamics

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

mÃ©na

-0.18

ibold

-0.15

ëĶĶìĭľ

-0.15

nonnull

-0.14

iaux

-0.14

abar

-0.14

filer

-0.14

joy

-0.14

èķ

-0.14

gebn

-0.14

POSITIVE LOGITS

 Suff

0.16

 transcript

0.16

Fus

0.15

 anch

0.15

 Said

0.14

 Sans

0.14

 coincidence

0.14

 Asked

0.14

Activations Density 0.072%

phrases that indicate opinions or commentary on player performance and team dynamics

No Comments

No Known Activations