INDEX

Explanations

phrases indicating conditions, specifications, or comparisons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 12-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L12R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.12.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

Viv

-0.14

Ð½Ð¾Ð¶

-0.14

stdClass

-0.14

eload

-0.14

eea

-0.14

anio

-0.13

iquer

-0.13

.rdf

-0.13

athom

-0.13

URT

-0.13

POSITIVE LOGITS

ienes

0.16

ffi

0.15

ushman

0.15

amas

0.15

rait

0.15

0.14

izioni

0.14

sac

0.14

erdale

0.14

icus

0.13

Activations Density 0.021%

phrases indicating conditions, specifications, or comparisons

No Comments

No Known Activations