INDEX

Explanations

words associated with various locations and settings

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

hips

-0.17

hir

-0.16

NESS

-0.16

izers

-0.16

_regeneration

-0.16

GenerationStrategy

-0.15

zers

-0.15

essel

-0.14

obody

-0.14

POSITIVE LOGITS

 dwell

0.29

side

0.26

-bound

0.25

dw

0.25

dw

0.24

-side

0.23

 dwelling

0.22

bound

0.22

-wide

0.21

 bound

0.20

Activations Density 0.266%

words associated with various locations and settings

No Comments

No Known Activations