INDEX

Explanations

references to social relationships and professional associations

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

ople

-0.17

bourne

-0.16

 Darling

-0.15

 Pruitt

-0.15

áº¯m

-0.14

istÃ©

-0.14

 ambit

-0.14

ÄĽl

-0.14

kola

-0.14

halt

-0.13

POSITIVE LOGITS

hip

0.17

 Shim

0.15

ship

0.15

hr

0.14

cul

0.14

uD

0.14

ERO

0.14

CJK

0.14

hl

0.14

assen

0.14

Activations Density 0.114%

references to social relationships and professional associations

No Comments

No Known Activations