INDEX

Explanations

phrases indicating actions, states, or abilities related to performing tasks or making commitments

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

aye

-0.14

 Tyto

-0.14

APPER

-0.14

á»±

-0.14

_macros

-0.14

 Marshall

-0.14

 interchange

-0.14

uez

-0.14

esson

-0.14

.docs

-0.13

POSITIVE LOGITS

itis

0.15

Wax

0.14

aden

0.14

 Radi

0.14

Ã©li

0.14

DSA

0.14

ereum

0.14

ads

0.14

PathParam

0.14

Activations Density 0.999%

phrases indicating actions, states, or abilities related to performing tasks or making commitments

No Comments

No Known Activations