INDEX

Explanations

phrases that indicate the presence or absence of hidden fees in a context of customer service or travel experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

hat

-0.14

iene

-0.14

ãģĶ

-0.13

sav

-0.13

pent

-0.13

oine

-0.13

Sav

-0.13

gne

-0.13

ighb

-0.13

anal

-0.13

POSITIVE LOGITS

shr

0.13

á»ĳng

0.13

ÑĩÐ°ÑģÑĤ

0.13

ebek

0.13

eros

0.13

rof

0.13

reta

0.13

agan

0.13

annies

0.13

Inf

0.13

Activations Density 0.096%

phrases that indicate the presence or absence of hidden fees in a context of customer service or travel experiences

No Comments

No Known Activations