INDEX

Explanations

references to historical events and periods, particularly related to wars

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 3-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L3R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.3.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

 Soap

-0.14

asy

-0.14

eldom

-0.14

æĭ³

-0.14

abled

-0.14

licer

-0.14

erule

-0.13

NJ

-0.13

ella

-0.13

POSITIVE LOGITS

imoto

0.18

ambient

0.15

aec

0.15

_nf

0.15

Ai

0.14

ÅĤe

0.14

 Barth

0.14

licos

0.14

hf

0.14

ickets

0.14

Activations Density 0.233%

references to historical events and periods, particularly related to wars

No Comments

No Known Activations

references to historical events and periods, particularly related to wars

No Comments

No Known Activations