INDEX

Explanations

historical dates and significant events related to individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 26-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L26R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.26.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

iaux

-0.18

ÏĩÎ¹

-0.17

TestingModule

-0.16

Calibri

-0.16

ocha

-0.16

ocator

-0.15

apus

-0.15

lesia

-0.15

ategorized

-0.15

æĿĤ

-0.15

POSITIVE LOGITS

0.54

0.52

0.50

0.49

0.47

0.44

0.43

Activations Density 0.098%

historical dates and significant events related to individuals

No Comments

No Known Activations