INDEX

Explanations

names of notable individuals, particularly those associated with family or historical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 16-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L16R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.16.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

enna

-0.16

elder

-0.15

 Wars

-0.15

notes

-0.14

-www

-0.14

 Jahres

-0.14

Ãªu

-0.14

igan

-0.14

URA

-0.14

anger

-0.13

POSITIVE LOGITS

ine

0.18

sson

0.18

IRECT

0.17

vale

0.15

seys

0.15

éĿ©

0.15

ovna

0.14

LOCKS

0.14

ussen

0.14

_lazy

0.14

Activations Density 0.083%

names of notable individuals, particularly those associated with family or historical contexts

No Comments

No Known Activations