INDEX

Explanations

episodic references related to specific episodes or installments of a television series

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 22-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L22R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.22.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

icorn

-0.15

uhn

-0.15

erce

-0.14

Äįin

-0.14

aÅ¼

-0.14

etty

-0.14

urf

-0.14

ernaut

-0.13

POSITIVE LOGITS

LIC

0.15

YO

0.14

achen

0.14

DownList

0.14

é¦Ļèķī

0.14

aine

0.14

ì§¸

0.13

çģ£

0.13

opoulos

0.13

Ð±ÑĥÑĢÐ³

0.13

Activations Density 0.061%

episodic references related to specific episodes or installments of a television series

No Comments

No Known Activations