INDEX

Explanations

references to roles, positions, and elements related to games and their structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 21-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L21R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.21.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

Glo

-0.15

dera

-0.15

cing

-0.14

alleries

-0.14

py

-0.14

ptal

-0.14

æ´ĭ

-0.14

æµ©

-0.14

 saddle

-0.14

 Turk

-0.14

POSITIVE LOGITS

sworth

0.15

 itself

0.15

icator

0.15

ÑĨÐ¸Ðº

0.15

ilim

0.14

åıĬåħ¶

0.14

egend

0.14

observ

0.14

npc

0.14

åĲįç§°

0.14

Activations Density 0.001%

references to roles, positions, and elements related to games and their structure

No Comments

No Known Activations