INDEX

Explanations

references to social media engagement actions, particularly related to "liking" and interactions on Facebook

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

.volley

-0.18

 Ulus

-0.16

elah

-0.15

.LayoutStyle

-0.15

vak

-0.15

andon

-0.15

ÑĦÑĦ

-0.15

BB

-0.15

arkers

-0.14

jem

-0.14

POSITIVE LOGITS

iro

0.17

IRO

0.16

equ

0.15

.DAO

0.14

 Gloss

0.14

itos

0.14

heritance

0.14

hashtags

0.14

Ã¤dchen

0.13

ãĤ

0.13

Activations Density 0.026%

references to social media engagement actions, particularly related to "liking" and interactions on Facebook

No Comments

No Known Activations