INDEX

Explanations

dates and time-related information

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

rÃ³

-0.15

 Nichols

-0.14

 Expl

-0.14

 Morris

-0.14

 Schwartz

-0.14

Expl

-0.14

arp

-0.14

aqu

-0.13

->

-0.13

 Press

-0.13

POSITIVE LOGITS

.***.***

0.15

 sharedApplication

0.15

ÎłÏģÎ¿

0.14

upe

0.14

ilog

0.14

ebek

0.14

ISTA

0.14

/gtest

0.14

 threadIdx

0.14

 diplom

0.13

Activations Density 0.034%

dates and time-related information

No Comments

No Known Activations