INDEX

Explanations

references to memory and cognitive functions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

endor

-0.16

led

-0.16

pas

-0.15

leta

-0.15

ereotype

-0.15

oler

-0.15

mund

-0.15

ode

-0.14

ino

-0.14

ackson

-0.14

POSITIVE LOGITS

 lane

0.25

brane

0.23

 Lane

0.20

_lane

0.19

 foam

0.19

 loss

0.18

 Foam

0.18

Lane

0.17

Jog

0.17

scape

0.17

Activations Density 0.030%

references to memory and cognitive functions

No Comments

No Known Activations