INDEX

Explanations

references to sports rankings and team performance

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

UNCTION

-0.15

hower

-0.14

 ÙĨØ¨

-0.14

dek

-0.14

Voj

-0.13

 LIABILITY

-0.13

esan

-0.13

Î±Î½Î¬

-0.13

Connect

-0.13

 connexion

-0.13

POSITIVE LOGITS

Gre

0.17

ritel

0.15

gre

0.15

Pin

0.15

0.14

æ¯ķ

0.14

uc

0.14

nested

0.14

etti

0.14

 Outer

0.14

Activations Density 0.005%

references to sports rankings and team performance

No Comments

No Known Activations