INDEX

Explanations

numerical values and their context within game statistics and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

okud

-0.15

inth

-0.14

ombo

-0.14

Nin

-0.14

å¤ļ

-0.13

edin

-0.13

 nineteenth

-0.13

embre

-0.12

nth

-0.12

atÃŃm

-0.12

POSITIVE LOGITS

0.28

0.26

0.25

0.24

0.23

Activations Density 0.654%

numerical values and their context within game statistics and measurements

No Comments

No Known Activations