INDEX

Explanations

references to individual players and their career statistics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 11-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L11R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.11.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

raÃ§

-0.15

hands

-0.15

_launcher

-0.15

vements

-0.14

hai

-0.14

ales

-0.14

UDO

-0.13

reesome

-0.13

ÐµÐ¹ÑģÑĤÐ²

-0.13

eres

-0.13

POSITIVE LOGITS

 visit

0.17

ulle

0.16

KE

0.15

chalk

0.15

emos

0.15

ãģŀ

0.15

 Ð±Ð¾Ð»ÐµÐ·Ð½Ð¸

0.14

_Helper

0.14

 Paramount

0.14

ª

0.13

Activations Density 0.090%

references to individual players and their career statistics

No Comments

No Known Activations