INDEX

Explanations

names of characters and significant individuals in narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 6-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L6R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.6.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

fty

-0.17

kud

-0.16

oje

-0.16

abella

-0.15

ekim

-0.15

allis

-0.14

laden

-0.13

åĹ

-0.13

unn

-0.13

erval

-0.13

POSITIVE LOGITS

Rank

0.15

Å¡ak

0.15

ubi

0.15

ibel

0.14

ky

0.14

Vul

0.14

lendir

0.14

ģ

0.14

itar

0.13

xfb

0.13

Activations Density 0.056%

names of characters and significant individuals in narratives

No Comments

No Known Activations