INDEX

Explanations

names of individuals and their associated actions or roles in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 14-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L14R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.14.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

quoise

-0.15

ObjectContext

-0.15

orous

-0.15

raÃ§

-0.14

occo

-0.14

htmlspecialchars

-0.13

æº

-0.13

.ObjectModel

-0.13

abcdefghijklmnop

-0.13

POSITIVE LOGITS

kowski

0.14

PCI

0.14

 depos

0.14

æ¤

0.14

elson

0.13

Jr

0.13

 eens

0.13

/Common

0.13

dk

0.13

 aras

0.13

Activations Density 0.102%

names of individuals and their associated actions or roles in various contexts

No Comments

No Known Activations