INDEX

Explanations

references to sources and citations in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 2-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L2R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.2.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

IGO

-0.17

.dk

-0.15

ropri

-0.14

ITO

-0.14

oro

-0.14

arella

-0.14

_relu

-0.13

.bc

-0.13

igo

-0.13

implements

-0.13

POSITIVE LOGITS

 ÑĥÑģ

0.16

 shar

0.16

sem

0.15

ernel

0.15

RED

0.14

Bir

0.14

ar

0.14

onz

0.14

anal

0.14

ktor

0.14

Activations Density 0.083%

references to sources and citations in text

No Comments

No Known Activations