INDEX

Explanations

dates and numerical references related to historical events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 13-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L13R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.13.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

 Garrett

-0.16

ihil

-0.15

ipar

-0.14

rick

-0.14

 unserialize

-0.14

 Malk

-0.14

okud

-0.14

 Gaul

-0.14

opsy

-0.13

_completion

-0.13

POSITIVE LOGITS

 alike

0.26

 respectively

0.20

assen

0.14

oud

0.14

0.13

 combo

0.13

reh

0.13

 chapters

0.13

 Licensed

0.13

ensive

0.13

Activations Density 0.029%

dates and numerical references related to historical events

No Comments

No Known Activations