INDEX

Explanations

numeric scores and outcomes in a competitive context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

áº»

-0.15

ECH

-0.14

otal

-0.14

ulner

-0.14

 Maul

-0.14

rum

-0.13

HELL

-0.13

à¥įà¤Ĺà¤¤

-0.13

_pen

-0.13

anni

-0.13

POSITIVE LOGITS

edia

0.15

,},↵

0.14

sko

0.14

åįĪ

0.14

yer

0.14

tainment

0.13

yen

0.13

EDIA

0.13

leh

0.13

dio

0.13

Activations Density 0.003%

numeric scores and outcomes in a competitive context

No Comments

No Known Activations