INDEX

Explanations

terms related to different types of rooms in a property description

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 5-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L5R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.5.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

ajar

-0.17

owe

-0.15

uÃŃ

-0.14

unma

-0.14

ow

-0.14

arkan

-0.14

zig

-0.14

eros

-0.14

achu

-0.14

POSITIVE LOGITS

atatype

0.15

Helvetica

0.15

estone

0.14

Î¬Î½Î±

0.14

ãĥĸãĥª

0.14

hide

0.14

iena

0.14

-hide

0.14

 Bolton

0.14

theon

0.13

Activations Density 0.018%

terms related to different types of rooms in a property description

No Comments

No Known Activations