INDEX

Explanations

key prepositions and conjunctions that indicate relationships

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 18-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L18R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.18.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

 Consequently

-0.15

auc

-0.15

secs

-0.15

 secs

-0.15

hy

-0.14

oster

-0.14

uzu

-0.14

olia

-0.13

_MB

-0.13

ë¿Ĳ

-0.13

POSITIVE LOGITS

allis

0.16

iene

0.15

 titular

0.15

enos

0.14

heim

0.14

iena

0.14

idenav

0.14

á»ĥ

0.14

 solidity

0.14

 popis

0.14

Activations Density 0.000%

key prepositions and conjunctions that indicate relationships

No Comments

No Known Activations