INDEX

Explanations

references to trust and relationships with individuals or organizations

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

 interesse

-0.15

charm

-0.15

ÑģÑİ

-0.15

quist

-0.14

ilon

-0.14

stanov

-0.14

.touches

-0.14

ÄĽle

-0.14

tesy

-0.14

POSITIVE LOGITS

 implicitly

0.24

 implicit

0.19

 judgment

0.19

implicitly

0.18

 abilities

0.18

ereo

0.16

 judgement

0.16

 Implicit

0.16

Implicit

0.15

implicit

0.15

Activations Density 0.089%

references to trust and relationships with individuals or organizations

No Comments

No Known Activations