INDEX

Explanations

season and episode information related to television shows

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 7-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L7R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.7.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

uelle

-0.16

ÑĤÑĢÐ°

-0.15

plusplus

-0.15

afil

-0.14

ibbon

-0.14

ective

-0.14

-0.13

ãĤªãĥª

-0.13

abajo

-0.13

pson

-0.13

POSITIVE LOGITS

 fitte

0.17

0.16

owy

0.15

.desktop

0.14

mini

0.14

ovi

0.14

.scalablytyped

0.14

éºĹ

0.14

.AppSettings

0.14

 mini

0.13

Activations Density 0.018%

season and episode information related to television shows

No Comments

No Known Activations