INDEX

Explanations

instances of irony and related expressions in various contexts

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

iloc

-0.16

ç£

-0.15

Ã©mon

-0.15

 prostituer

-0.15

ÐºÑĢÐµÑĤ

-0.15

 interp

-0.15

IDEO

-0.15

aggio

-0.15

loy

-0.15

PTY

-0.15

POSITIVE LOGITS

otor

0.17

Sie

0.16

æĺ¾

0.15

utra

0.15

inde

0.15

fe

0.15

vere

0.15

0.14

pur

0.14

Activations Density 0.230%

instances of irony and related expressions in various contexts

No Comments

No Known Activations