INDEX

Explanations

mentions of television series and their details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 25-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L25R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.25.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

 cast

-0.16

 Jahres

-0.15

Eag

-0.15

markt

-0.15

formats

-0.14

 casts

-0.14

 Downing

-0.14

ÐµÐ²Ñĸ

-0.14

Ìģ

-0.14

ecta

-0.14

POSITIVE LOGITS

ER

0.20

kiye

0.18

 NYPD

0.17

CSI

0.16

CSI

0.16

unte

0.16

ER

0.15

ERING

0.15

iami

0.15

_INCLUDED

0.15

Activations Density 0.047%

mentions of television series and their details

No Comments

No Known Activations