INDEX

Explanations

conjunctions and their associations with positive attributes or 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

hall

-0.15

ternal

-0.14

ÙĬÙĩ

-0.14

Az

-0.14

*-

-0.14

RX

-0.14

omnia

-0.14

 Phoenix

-0.13

ä¿

-0.13

 Mobility

-0.13

POSITIVE LOGITS

ondo

0.16

AndWait

0.15

peg

0.14

/goto

0.14

 Absolute

0.14

rog

0.14

onda

0.14

.exc

0.14

0.13

wom

0.13

Activations Density 0.069%

conjunctions and their associations with positive attributes or relationships

No Comments

No Known Activations