INDEX

Explanations

references to trauma and its variants

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 24-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L24R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.24.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

commerce

-0.17

iw

-0.16

vin

-0.16

isle

-0.16

pie

-0.15

bus

-0.15

MOTE

-0.15

ÏĢÎ¿Ïį

-0.14

ropy

-0.14

POSITIVE LOGITS

Tra

0.27

uma

0.24

-tra

0.23

Tra

0.23

tra

0.23

umatic

0.21

 trauma

0.19

umas

0.19

jectories

0.19

jectory

0.18

Activations Density 0.013%

references to trauma and its variants

No Comments

No Known Activations