INDEX

Explanations

references to people and their roles or occupations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 31-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L31R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.31.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

 Erotische

-0.15

variant

-0.14

lemn

-0.14

zas

-0.14

ilst

-0.14

offee

-0.13

ertia

-0.13

oker

-0.13

estring

-0.13

áº§n

-0.13

POSITIVE LOGITS

 uomo

0.21

 profess

0.21

 presidente

0.20

 socio

0.19

 studios

0.19

 console

0.19

mec

0.19

 vice

0.18

 consul

0.18

nip

0.18

Activations Density 0.018%

references to people and their roles or occupations

No Comments

No Known Activations