INDEX

Explanations

references to names or entities in professional contexts

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

 Salmon

-0.16

 salmon

-0.15

 Salman

-0.14

 bitcoin

-0.14

ŃĲï¸ı

-0.14

owie

-0.13

 norsk

-0.13

è¿½

-0.13

asio

-0.13

VAR

-0.13

POSITIVE LOGITS

Hud

0.35

 inmate

0.32

 prison

0.32

 prisons

0.32

 inmates

0.32

 Prison

0.31

 prisoners

0.31

 prisoner

0.29

 incarceration

0.24

 incarcerated

0.24

Activations Density 0.003%

references to names or entities in professional contexts

No Comments

No Known Activations