INDEX

Explanations

words and phrases related to entertainment, specifically watching television and engaging in leisure activities

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L8R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.8.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

exus

-0.17

oli

-0.16

utos

-0.15

.appspot

-0.14

ÐµÐ¹

-0.14

FT

-0.14

cribe

-0.14

ays

-0.14

NSBundle

-0.14

chez

-0.13

POSITIVE LOGITS

enga

0.16

enty

0.15

landa

0.14

agal

0.14

desk

0.14

issant

0.13

ibar

0.13

 Drivers

0.13

quina

0.13

ulls

0.13

Activations Density 0.300%

words and phrases related to entertainment, specifically watching television and engaging in leisure activities

No Comments

No Known Activations