INDEX

Explanations

references to urban characteristics and environments

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

OME

-0.17

atk

-0.16

oples

-0.16

lessly

-0.15

leton

-0.15

rokes

-0.15

htar

-0.15

olin

-0.15

aus

-0.15

POSITIVE LOGITS

ization

0.31

ized

0.28

ites

0.28

/sub

0.26

 renewal

0.24

ite

0.24

isation

0.23

izing

0.21

icity

0.21

/r

0.21

Activations Density 0.010%

references to urban characteristics and environments

No Comments

No Known Activations