INDEX

Explanations

references to programming or formatting commands

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

icari

-0.15

 sensit

-0.15

ÑģÐ»Ð¸

-0.15

isti

-0.15

Ã´t

-0.15

iglia

-0.14

 odbor

-0.14

vail

-0.14

Lag

-0.14

aca

-0.14

POSITIVE LOGITS

usher

0.15

 Rover

0.15

_STACK

0.15

.nlm

0.14

.nih

0.14

 Torch

0.14

 thunk

0.13

errick

0.13

 Belt

0.13

Activations Density 0.002%

references to programming or formatting commands

No Comments

No Known Activations