INDEX

Explanations

references to time-specific events or dates

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

fnlp/Llama3_1-8B-Base-LXR-8x/Llama3_1-8B-Base-L1R-8x

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

cerebras/SlimPajama-627B

Features

32,768

Data Type

bfloat16

Hook Name

blocks.1.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

ay

-0.16

 ball

-0.16

Blo

-0.15

 speech

-0.15

uti

-0.14

ayas

-0.14

 Hollow

-0.14

ethe

-0.14

aga

-0.13

 Spiel

-0.13

POSITIVE LOGITS

ties

0.16

stadt

0.16

 milano

0.16

 lyon

0.14

 Clint

0.14

iant

0.14

immer

0.14

áºŃn

0.14

ohn

0.14

igu

0.14

Activations Density 0.077%

references to time-specific events or dates

No Comments

No Known Activations