INDEX

Explanations

emotions and sensory experiences within the narrative

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 30-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L30R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.30.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

AXB

-0.16

 ours

-0.15

åĤ·

-0.14

amage

-0.14

 temperament

-0.14

Psr

-0.14

æĻ´

-0.14

bler

-0.13

æĺ¾

-0.13

 Interrupt

-0.13

POSITIVE LOGITS

 sensations

0.26

 goose

0.25

 sensation

0.25

 surge

0.25

 rush

0.23

 pins

0.23

 ting

0.22

 wave

0.21

rush

0.20

pins

0.20

Activations Density 0.277%

emotions and sensory experiences within the narrative

No Comments

No Known Activations