INDEX

Explanations

various types of written works or literary outputs

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

alar

-0.15

oupon

-0.15

ifax

-0.15

pcf

-0.15

Ð³Ð°ÑĢ

-0.14

alars

-0.14

utar

-0.14

ngth

-0.13

OT

-0.13

umar

-0.13

POSITIVE LOGITS

ÛĮØ²

0.17

rog

0.17

kowski

0.17

insky

0.16

angep

0.16

adel

0.16

å§ĵ

0.15

riba

0.15

Qed

0.14

owski

0.14

Activations Density 0.030%

various types of written works or literary outputs

No Comments

No Known Activations