INDEX

Explanations

references to playoff games and postseason activities

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

Ci

-0.18

yun

-0.17

heet

-0.17

ulture

-0.15

tal

-0.15

å¿µ

-0.15

cola

-0.15

 ÑģÐ²Ð¸

-0.15

Ci

-0.15

ASA

-0.14

POSITIVE LOGITS

agy

0.17

dry

0.17

dry

0.17

iffe

0.17

asco

0.14

èĲ½ãģ¡

0.14

(LP

0.14

 Ð¯Ðº

0.14

 Decompiled

0.14

-overlay

0.14

Activations Density 0.016%

references to playoff games and postseason activities

No Comments

No Known Activations