INDEX

Explanations

mentions of various television channels and programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

alue

-0.17

ladu

-0.16

anja

-0.15

olume

-0.15

olta

-0.15

fern

-0.15

Ð°ÑĪ

-0.15

 spit

-0.14

oreach

-0.14

RAR

-0.14

POSITIVE LOGITS

ech

0.19

eral

0.18

eur

0.16

eu

0.16

ruba

0.15

mercial

0.15

 versa

0.14

\V

0.14

smarty

0.14

Til

0.14

Activations Density 0.159%

mentions of various television channels and programming

No Comments

No Known Activations