INDEX

Explanations

personal identifiers and biographical details

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With LLAMA3.1-8B @ 20-llamascope-res-32k

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L20R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.20.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

weit

-0.14

 Interracial

-0.14

ington

-0.14

ingleton

-0.14

trak

-0.14

 Persist

-0.13

 ÙħØ´

-0.13

occupied

-0.13

richt

-0.13

Ã¡r

-0.13

POSITIVE LOGITS

 native

0.72

 born

0.63

native

0.59

 natives

0.58

 Born

0.57

born

0.56

-native

0.53

Born

0.52

-born

0.50

/native

0.44

Activations Density 0.317%

personal identifiers and biographical details

No Comments

No Known Activations